© 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. 68881
    Prev
    Next
    INDEX
    Explanations

    before, ban, drug, refunds, smooth, children

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

    SQL, Vector, precursors

    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
     समिति
    0.51
    FRINGEMENT
    0.50
     simonsen
    0.49
    ETTE
    0.49
    ANDER
    0.48
    LEY
    0.47
     subcommittee
    0.47
    頎
    0.46
    филлер
    0.46
     CLARK
    0.46
    POSITIVE LOGITS
     Mathematics
    0.48
     Conjug
    0.47
     Pascal
    0.46
     kelamin
    0.46
     mathemat
    0.44
     Canc
    0.43
     Sandro
    0.42
    osexuality
    0.41
     l
    0.41
     equations
    0.41
    Activations Density 0.002%

    No Known Activations