© 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. 90303
    Prev
    Next
    INDEX
    Explanations

    need to, story through, $1, please join, business while

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

    numbers and instructions

    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
     angered
    0.48
     "'";
    0.48
     Ayr
    0.46
    pyrim
    0.43
     amassed
    0.43
     angrily
    0.43
     Dall
    0.43
     are
    0.43
     "*");
    0.43
     Hert
    0.42
    POSITIVE LOGITS
    lz
    0.47
    OW
    0.46
    iv
    0.46
    Теперь
    0.46
    lp
    0.45
     Кстати
    0.45
    篱
    0.45
    र्ने
    0.45
    DICTION
    0.44
    Always
    0.44
    Activations Density 0.001%

    No Known Activations