© 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. 114982
    Prev
    Next
    INDEX
    Explanations

    successful effective

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

    initial technical terms

    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
    in
    0.53
    jska
    0.45
    揪
    0.44
    في
    0.43
     variabili
    0.43
     வெப்ப
    0.43
    Metering
    0.43
    ervis
    0.42
     pourraient
    0.42
     violência
    0.42
    POSITIVE LOGITS
     pretended
    0.48
     Kı
    0.46
    有两个
    0.45
     can
    0.45
     pretending
    0.45
     speł
    0.44
     tenga
    0.44
    섯
    0.44
    คง
    0.43
     Kik
    0.43
    Activations Density 0.000%

    No Known Activations