© 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. 88941
    Prev
    Next
    INDEX
    Explanations

    work week, with adding, to put

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

    numbers and calculations

    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
    الص
    0.48
     ডু
    0.48
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.47
    دم
    0.47
    தமிழ்
    0.47
    Otro
    0.45
    ”।
    0.44
    гів
    0.44
    erzo
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
    POSITIVE LOGITS
    ure
    0.45
     शाही
    0.43
     hydrogen
    0.42
     streaming
    0.41
    urate
    0.41
     seren
    0.41
    uret
    0.41
    ural
    0.41
     objekt
    0.41
     lecturer
    0.40
    Activations Density 0.001%

    No Known Activations