© 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. 64758
    Prev
    Next
    INDEX
    Explanations

    mention Alison Greenhalgh

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

    finding first word

    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
    衽
    0.48
     वर्कशीट
    0.46
    เร
    0.46
     பூ
    0.46
    เบ
    0.45
    व्र
    0.45
    嶷
    0.45
     סי
    0.45
    公园
    0.45
     देवगन
    0.45
    POSITIVE LOGITS
    ols
    0.49
     )$
    0.43
     lemn
    0.38
    hi
    0.38
     screened
    0.38
    olz
    0.38
    <>
    0.38
     گذ
    0.38
     Specify
    0.38
    ucine
    0.37
    Activations Density 0.000%

    No Known Activations