© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14198
    Prev
    Next
    INDEX
    Explanations

    index followed by punctuation

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

    The neuron reliably fires on single‐letter mathematical symbols used as indices or parameters (e.g. “i,” “j,” “k,” “n”) within equations.

    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
     it
    -1.40
     different
    -1.30
     following
    -1.23
     varieties
    -1.22
     types
    -1.16
     gespannt
    -1.14
     virtues
    -1.14
     several
    -1.11
     from
    -1.10
     einigen
    -1.09
    POSITIVE LOGITS
    นี้
    1.55
    躋
    1.45
    ILERS
    1.37
    有點
    1.33
     berkualitas
    1.29
    ใคร
    1.25
     impulsar
    1.23
    ﷺ
    1.23
    這是
    1.21
    //}
    1.18
    Activations Density 0.027%

    No Known Activations