© 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. 255095
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    匡
    0.47
     huyền
    0.43
    题
    0.41
     युद्ध
    0.41
    統合
    0.40
     Gottes
    0.40
    ✍
    0.40
    闡
    0.39
     त्याच्या
    0.39
     भाऊ
    0.38
    POSITIVE LOGITS
    in
    0.59
     attractiveness
    0.52
     optimism
    0.47
     berharap
    0.47
     fotos
    0.46
     germination
    0.46
    rop
    0.46
    happy
    0.46
    endam
    0.46
     esperan
    0.46
    Activations Density 0.002%

    No Known Activations