© 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. 106932
    Prev
    Next
    INDEX
    Explanations

    report guests tend

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

    polarity, niche, astral

    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
     endorsement
    0.44
     conco
    0.43
     industry
    0.43
     exhaustive
    0.43
     *>(
    0.42
    주고
    0.42
    蛆
    0.42
     logout
    0.42
     came
    0.41
    োগ্র
    0.41
    POSITIVE LOGITS
    <0x0D>
    0.54
     Ush
    0.52
    vic
    0.50
     ព
    0.50
     البيت
    0.46
     rừng
    0.45
    菸
    0.45
    </h1>
    0.45
    u
    0.45
    </h4>
    0.44
    Activations Density 0.000%

    No Known Activations