© 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. 90223
    Prev
    Next
    INDEX
    Explanations

    wear late

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

    booty

    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
     Jefe
    0.48
    ционным
    0.47
    _
    0.47
     Supreme
    0.44
    intermediate
    0.44
    Intermediate
    0.43
    setMaximum
    0.43
    ного
    0.42
    Tiempo
    0.42
    डिएट
    0.42
    POSITIVE LOGITS
     matroid
    0.53
     Ét
    0.49
     ไว้
    0.49
    ❆
    0.48
    专
    0.46
    🚞
    0.46
     fibres
    0.46
    }}}{\
    0.46
     Wendy
    0.45
     én
    0.45
    Activations Density 0.000%

    No Known Activations