© 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. 66626
    Prev
    Next
    INDEX
    Explanations

    location and area

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

    draws patterns preceding certain 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
     H
    0.52
    -
    0.51
     Irak
    0.50
     Matt
    0.49
     phoned
    0.47
     reported
    0.46
     I
    0.46
     ​​
    0.45
     Detta
    0.45
     ishlab
    0.44
    POSITIVE LOGITS
    elementAt
    0.52
    วัต
    0.52
     가까
    0.48
     따라서
    0.48
    牖
    0.47
    튜디오
    0.45
    뭅
    0.45
    늉
    0.45
    ทุกคน
    0.44
     স্থষ্টি
    0.44
    Activations Density 0.001%

    No Known Activations