© 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. 100991
    Prev
    Next
    INDEX
    Explanations

    contractions starting with i or there

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

    founded in, carries, more robust, little difficulty

    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
     spielen
    0.50
    target
    0.48
     स्टाइल
    0.47
    iteit
    0.47
    ,_
    0.46
    होम
    0.46
    umna
    0.46
    ObjectUnderTest
    0.44
     टारगेट
    0.44
    p
    0.44
    POSITIVE LOGITS
     이상의
    0.56
     M
    0.48
    锜
    0.48
     Acosta
    0.46
     상
    0.46
    〓
    0.46
     정상
    0.45
     Masaki
    0.45
    ダメ
    0.45
     Є
    0.45
    Activations Density 0.014%

    No Known Activations