© 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. 20727
    Prev
    Next
    INDEX
    Explanations

    another, yet, 4, Cent

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

    AI, he, states, analysis

    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
    tobago
    0.57
    йся
    0.55
     COc
    0.50
    ಾಗುತ್ತದೆ
    0.50
     गंभीर
    0.48
     Gabe
    0.48
    ivad
    0.48
    ᱘
    0.47
    क्षिप्त
    0.47
    砶
    0.47
    POSITIVE LOGITS
    0
    0.64
    c
    0.52
    3
    0.52
     analyse
    0.51
    支
    0.50
     parse
    0.50
    4
    0.47
    <
    0.46
    an
    0.45
    Type
    0.45
    Activations Density 0.000%

    No Known Activations