© 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. 54956
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

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

    describing pictures and photos

    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
    seqNum
    0.49
    $&$-
    0.45
     తల్లి
    0.44
    ldef
    0.43
    FBSDKGraph
    0.43
     irgendwie
    0.43
     яе
    0.43
    esquerdo
    0.42
    ভূম
    0.41
     ながら
    0.41
    POSITIVE LOGITS
     pulang
    0.49
     peny
    0.48
    ب
    0.48
     mengunjungi
    0.48
    ه
    0.48
    欢乐
    0.47
     bekerja
    0.46
    a
    0.46
     sebanyak
    0.46
     pengh
    0.45
    Activations Density 0.000%

    No Known Activations