© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3523
    Prev
    Next
    INDEX
    Explanations

    parameter estimation

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

    The neuron detects occurrences of the word “Parameter” (e.g. in ParameterizedTypeReference or ParameterMissing errors) in code contexts.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    絵本
    -0.97
    )
    -0.94
     πρώ
    -0.94
     religione
    -0.93
     doubtless
    -0.92
     않았
    -0.92
    ﮑ
    -0.91
     Now
    -0.91
     ottoman
    -0.91
     sax
    -0.91
    POSITIVE LOGITS
    isation
    1.44
    izations
    1.41
    ised
    1.39
    ization
    1.28
    稣
    1.27
    digm
    1.27
     régionales
    1.17
    licy
    1.16
    parameter
    1.15
     Paramètres
    1.15
    Activations Density 0.021%

    No Known Activations