© 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. 161297
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

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

    describing states and sequences

    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
    日前
    0.51
    えた
    0.49
     its
    0.46
    भ
    0.45
     throttle
    0.44
    ी
    0.42
     market
    0.41
    トル
    0.40
    शीर
    0.40
    ित
    0.40
    POSITIVE LOGITS
    葲
    0.50
    盞
    0.49
     कैल्शियम
    0.48
    衙
    0.47
    <unused1060>
    0.47
     Yards
    0.46
     ગ્ર
    0.46
    hitva
    0.46
    Veg
    0.46
     ಏನು
    0.46
    Activations Density 0.001%

    No Known Activations