© 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. 155844
    Prev
    Next
    INDEX
    Explanations

    slot canyon

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

    music, body language, Oxford comma

    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
    谕
    0.52
    abr
    0.49
    绸
    0.47
    amaks
    0.46
    授予
    0.46
    fptr
    0.44
    仪
    0.44
    ătur
    0.44
     лиц
    0.44
    âmica
    0.44
    POSITIVE LOGITS
     melody
    0.54
     biochemistry
    0.52
     dilengkapi
    0.50
    נ
    0.49
     raison
    0.49
     physiology
    0.48
    レビュー
    0.48
     Ereign
    0.48
     hating
    0.47
    ולנד
    0.47
    Activations Density 0.000%

    No Known Activations