© 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. 17643
    Prev
    Next
    INDEX
    Explanations

    quantities and numbers

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

    error condition handling

    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
     H
    0.58
     L
    0.54
     UTC
    0.53
     Q
    0.51
     LIGO
    0.50
     "
    0.50
     Investigators
    0.49
     Hon
    0.48
     Distinguished
    0.47
     U
    0.47
    POSITIVE LOGITS
    갔
    0.50
     तालाब
    0.47
    Flicky
    0.47
    ngày
    0.47
     chủng
    0.47
    嫖
    0.46
    สุด
    0.45
     riguardo
    0.45
    amot
    0.45
    ambiental
    0.45
    Activations Density 0.000%

    No Known Activations