© 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. 242118
    Prev
    Next
    INDEX
    Explanations

    to: and or

    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
    зит
    0.50
    멤
    0.49
    σεις
    0.46
    加坡
    0.45
     శాతం
    0.45
    渲
    0.45
    সিডেন্ট
    0.45
    زمة
    0.45
     Gericht
    0.45
    род
    0.44
    POSITIVE LOGITS
     정의
    0.48
     determinant
    0.45
    nl
    0.45
     corner
    0.44
    nid
    0.44
     composing
    0.44
    prediction
    0.43
     (=
    0.43
     置
    0.43
     spectacles
    0.43
    Activations Density 0.000%

    No Known Activations