© 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. 174161
    Prev
    Next
    INDEX
    Explanations

    website, www, chrome, band

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

    resource

    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
    ubishi
    0.55
     काळात
    0.48
    arus
    0.47
     auditors
    0.46
     atheist
    0.46
     lice
    0.46
    陇
    0.46
    books
    0.46
    denom
    0.45
    leet
    0.45
    POSITIVE LOGITS
     சட்ட
    0.47
    閃
    0.47
     liya
    0.44
    ırmaya
    0.44
     &#
    0.43
     σημα
    0.43
    ANNOT
    0.42
     surfacing
    0.42
    σ
    0.42
    maya
    0.42
    Activations Density 0.000%

    No Known Activations