© 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. 77797
    Prev
    Next
    INDEX
    Explanations

    business relations and descriptions

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

    learning rate

    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
     Dalit
    0.52
     было
    0.50
     було
    0.45
     ειδ
    0.44
     মহাম
    0.44
    匁
    0.43
    <unused2197>
    0.42
     Decl
    0.42
     கடுமையான
    0.42
     восем
    0.42
    POSITIVE LOGITS
    好
    0.55
    orar
    0.49
    ouni
    0.44
    前后
    0.43
    ào
    0.42
    ้อง
    0.42
    est
    0.42
    參
    0.42
     bn
    0.41
    F
    0.41
    Activations Density 0.001%

    No Known Activations