© 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. 143119
    Prev
    Next
    INDEX
    Explanations

    invoice, latitude, captioned, hair

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

    instructions and guidance

    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
    <0xAE>
    0.47
    開始
    0.47
    İK
    0.47
     breathed
    0.46
    /
    0.45
     GIRL
    0.43
     LOW
    0.42
     compound
    0.42
    QUIN
    0.41
    ic
    0.41
    POSITIVE LOGITS
    ی
    0.48
    قات
    0.47
    ग्विजय
    0.46
    फॉर्मेशन
    0.46
     रिश्
    0.45
     موم
    0.44
    طان
    0.43
    视野
    0.43
     रीठा
    0.43
    views
    0.43
    Activations Density 0.001%

    No Known Activations