© 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. 88815
    Prev
    Next
    INDEX
    Explanations

    Improvement and features

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

    improving or making better

    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
    "/"
    0.54
     ചോ
    0.50
     റോ
    0.49
    schap
    0.48
     tiềm
    0.48
     hunted
    0.48
     LOTRAchievement
    0.48
    ోంది
    0.47
    ആര്‍
    0.46
    祹
    0.46
    POSITIVE LOGITS
     Improve
    0.55
     mejorar
    0.50
    ↵↵
    0.49
     proveedores
    0.49
    Improve
    0.48
    ns
    0.48
     améli
    0.47
    as
    0.46
    improve
    0.46
    https
    0.46
    Activations Density 0.000%

    No Known Activations