© 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. 51872
    Prev
    Next
    INDEX
    Explanations

    lists enumerate options

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

    specific entities and concepts

    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
    ῴ
    0.51
    шат
    0.51
    ität
    0.50
    annten
    0.50
    лаве
    0.50
    шке
    0.50
     soát
    0.50
     failings
    0.49
    㧡
    0.49
     Elat
    0.48
    POSITIVE LOGITS
    Forest
    0.47
     on
    0.46
     करुन
    0.44
    ang
    0.44
    forestry
    0.44
    Row
    0.43
     by
    0.43
    0
    0.43
    emb
    0.43
    embed
    0.43
    Activations Density 0.000%

    No Known Activations