© 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. 157613
    Prev
    Next
    INDEX
    Explanations

    pc or gateway

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

    URLs with dimensions or signature

    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
    Primary
    0.48
    प्ली
    0.43
    ா
    0.43
     badi
    0.43
     पूरा
    0.43
     독일
    0.43
     klart
    0.42
    PRIMARY
    0.42
    ujemo
    0.42
     জার্মান
    0.41
    POSITIVE LOGITS
    ใส่
    0.43
    FuncName
    0.42
    ──
    0.41
     ministers
    0.41
    劲
    0.41
    тат
    0.40
     whey
    0.40
     વ્ય
    0.40
     Therapeutics
    0.40
     شراب
    0.40
    Activations Density 0.001%

    No Known Activations