© 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. 20996
    Prev
    Next
    INDEX
    Explanations

    tests your understanding

    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
     ప్రీ
    0.43
    ａ
    0.42
     カー
    0.42
     কানা
    0.40
     Β
    0.39
     এখনই
    0.39
    つ
    0.39
     সপ্তাহে
    0.38
     セ
    0.38
    ホース
    0.37
    POSITIVE LOGITS
     apl
    0.42
    mber
    0.42
    Apl
    0.41
     is
    0.40
     apel
    0.40
    wym
    0.39
     was
    0.39
     मानवीय
    0.39
     spite
    0.39
     cukup
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.