© 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. 25476
    Prev
    Next
    INDEX
    Explanations

    certain fat

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

    departments and finance

    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
    م
    0.60
     converters
    0.53
     Aga
    0.50
    مت
    0.50
    м
    0.49
     disks
    0.48
    in
    0.47
     circles
    0.47
    m
    0.47
    z
    0.47
    POSITIVE LOGITS
     하나의
    0.44
     pośred
    0.42
     பெரும்பாலும்
    0.42
    RESOURCE
    0.42
     കാര
    0.42
     স্থাপন
    0.41
     പിന്നീ
    0.41
    ’।
    0.41
    കാര
    0.41
    ཎ
    0.41
    Activations Density 0.000%

    No Known Activations