© 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. 240232
    Prev
    Next
    INDEX
    Explanations

    children and specific items

    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
    as
    0.57
    ell
    0.50
    eg
    0.50
    fmt
    0.49
    道
    0.49
    㭚
    0.49
    aw
    0.49
    esh
    0.47
    近
    0.47
    ern
    0.47
    POSITIVE LOGITS
     suede
    0.53
     apakah
    0.53
    ベビー
    0.53
     ankle
    0.52
     sulphide
    0.52
     hatchback
    0.51
     eraser
    0.51
     keychain
    0.51
     dítě
    0.50
     nightclub
    0.49
    Activations Density 0.000%

    No Known Activations