© 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. 145005
    Prev
    Next
    INDEX
    Explanations

    basal cell carcinoma

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

    jokes about stereotypes

    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
    s
    0.68
    ы
    0.54
    ی
    0.52
     Weekend
    0.50
    é
    0.48
    weekend
    0.48
     weekend
    0.47
    i
    0.47
    uper
    0.46
    <sup>
    0.46
    POSITIVE LOGITS
    सर्गिक
    0.54
     genomen
    0.47
    ζε
    0.47
     diminution
    0.47
    友人
    0.46
     সমাজের
    0.46
    यत
    0.45
     chewed
    0.45
     đúng
    0.44
    ತ್ನ
    0.43
    Activations Density 0.000%

    No Known Activations