© 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. 104130
    Prev
    Next
    INDEX
    Explanations

    conclusion

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

    lack or limitation

    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
    齐全
    0.53
     и
    0.50
    1
    0.50
    Minimum
    0.49
    4
    0.48
    2
    0.48
    Locations
    0.47
    ประจำ
    0.47
     trovano
    0.46
     the
    0.46
    POSITIVE LOGITS
     morphism
    0.46
    symplectic
    0.46
     hiyo
    0.46
    <unused76>
    0.46
     intestino
    0.46
     zásobníku
    0.45
     обстоятельства
    0.45
     टेंपरेचर
    0.45
     monopolist
    0.45
     pathophysiology
    0.45
    Activations Density 0.001%

    No Known Activations