© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103433
    Prev
    Next
    INDEX
    Explanations

    covariance, covariant, covalent

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to statistical analysis, particularly "covariance" and variants like "covariant" and "covariability".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on “covar”-root terms (e.g. covariance, covariate, covariability, covariant, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -2.55
    इटम
    -2.52
    ᕱ
    -2.44
    C
    -2.30
     combinar
    -2.22
    ooo
    -2.22
     laquelle
    -2.17
    ﮨ
    -2.14
    鸶
    -2.13
     memahami
    -2.08
    POSITIVE LOGITS
     tetapi
    2.92
    定休日
    2.56
    0
    2.41
    瀀
    2.27
     iſt
    2.22
     But
    2.17
     während
    2.14
     of
    2.14
     “
    2.13
    戩
    2.13
    Activations Density 0.004%

    No Known Activations