© 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. 124201
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    undertone, change, correct, smell

    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
    ikat
    0.50
    嘶
    0.47
    šu
    0.46
     to
    0.46
    E
    0.45
    ěl
    0.45
    ynchronous
    0.44
    ы
    0.44
     I
    0.43
    ands
    0.43
    POSITIVE LOGITS
     dowol
    0.54
     sente
    0.50
     subiect
    0.49
    tc
    0.49
    エム
    0.48
     gevallen
    0.48
    クセル
    0.48
    르
    0.48
     били
    0.47
     imedi
    0.47
    Activations Density 0.000%

    No Known Activations