© 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. 48068
    Prev
    Next
    INDEX
    Explanations

    Hamilton

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

    Stop supporting

    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
    5
    0.50
    ５
    0.48
    ת
    0.47
    хара
    0.46
    ริญ
    0.45
     кстати
    0.44
     смесь
    0.43
    теры
    0.43
    ५
    0.43
     главного
    0.43
    POSITIVE LOGITS
    TX
    0.54
     Zil
    0.49
     CSI
    0.48
    Mid
    0.48
     Ö
    0.48
     Hamilton
    0.48
     Ü
    0.47
     tx
    0.47
     Tx
    0.47
     POSSIBILITY
    0.47
    Activations Density 0.000%

    No Known Activations