© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19977
    Prev
    Next
    INDEX
    Explanations

    importing modules

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

    import React

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jn
    0.48
    ポー
    0.46
    _[
    0.45
     liberated
    0.45
     inactiv
    0.45
    protein
    0.44
    中に
    0.43
    wang
    0.42
    き
    0.41
    loving
    0.41
    POSITIVE LOGITS
    től
    0.52
     createElement
    0.46
     ହ
    0.45
     نح
    0.44
     {
    0.44
    PropTypes
    0.44
     from
    0.43
    స్కీ
    0.43
     axios
    0.42
    事先
    0.42
    Activations Density 0.000%

    No Known Activations