© 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-16K
    7. 12617
    Prev
    Next
    INDEX
    Explanations

    notice

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

    favorite cake, ∫, sauce, unexpected

    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_16k_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
     subterr
    0.49
     depress
    0.46
     BET
    0.45
    <tr>
    0.45
    entious
    0.44
     benda
    0.44
     nanot
    0.43
     pessim
    0.43
     barter
    0.43
    今回
    0.42
    POSITIVE LOGITS
    የ
    0.55
    chino
    0.46
    ักษณะ
    0.45
    compliance
    0.44
     ลักษณะ
    0.44
    Rahul
    0.44
    те
    0.43
     Always
    0.42
    ecommerce
    0.42
    wikimedia
    0.42
    Activations Density 0.020%

    No Known Activations