© 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. 208264
    Prev
    Next
    INDEX
    Explanations

    winnings

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

    go fish

    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
     rikt
    0.59
    刬
    0.55
    ミノ
    0.52
    𝑻
    0.51
     precisión
    0.49
    ショナル
    0.48
    𝐍
    0.48
     নির্ভ
    0.48
    𝓗
    0.47
     músculos
    0.47
    POSITIVE LOGITS
     auctions
    0.49
     www
    0.47
     waterproofing
    0.47
     Evolution
    0.45
     evolution
    0.44
    ambient
    0.44
     auction
    0.43
     a
    0.43
    quium
    0.43
     Frequent
    0.42
    Activations Density 0.001%

    No Known Activations