© 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. 248522
    Prev
    Next
    INDEX
    Explanations

    before a state or action

    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
    8
    0.51
    Alternative
    0.51
     마무리
    0.50
     I
    0.45
    alliative
    0.45
    ೮
    0.45
    alternative
    0.45
    Possible
    0.45
    ilized
    0.45
    ラスト
    0.43
    POSITIVE LOGITS
    র্ড
    0.51
     remaster
    0.51
     অপারে
    0.51
     certamente
    0.48
     đều
    0.47
    ভেট
    0.47
    াধ্য
    0.47
    崢
    0.46
    র্ডার
    0.46
     archiv
    0.45
    Activations Density 0.000%

    No Known Activations