© 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. 161216
    Prev
    Next
    INDEX
    Explanations

    financial receipts and dates

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

    foreign language words

    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
     redesigned
    0.50
     torno
    0.45
     );
    0.43
     pinMode
    0.43
    mps
    0.42
     нео
    0.42
     tch
    0.41
     справо
    0.41
    expanded
    0.41
     चर
    0.41
    POSITIVE LOGITS
    你要
    0.49
    ين
    0.49
    其他人
    0.48
    ?")
    0.48
    你
    0.47
    有人
    0.46
     bạn
    0.46
    你在
    0.45
    Я
    0.45
    你們
    0.44
    Activations Density 0.001%

    No Known Activations