© 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. 8290
    Prev
    Next
    INDEX
    Explanations

    finding, choosing, understanding

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

    agreement and 'in a'

    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
     rappro
    0.31
    乾
    0.31
    パン
    0.30
    ushroom
    0.29
    stringValue
    0.29
    েন্দ
    0.29
    тка
    0.29
    languageTag
    0.29
     testicule
    0.28
    넹
    0.28
    POSITIVE LOGITS
     ciência
    0.33
    founded
    0.32
     Starring
    0.31
     revel
    0.31
     city
    0.30
     Glasgow
    0.30
     CITY
    0.29
     Kiy
    0.29
     founded
    0.29
     kini
    0.29
    Activations Density 0.110%

    No Known Activations