© 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. 142094
    Prev
    Next
    INDEX
    Explanations

    financial documents and locations

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

    executable files and potential analysis

    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
    :
    0.47
    1
    0.46
    ’)
    0.46
    囃
    0.45
    渚
    0.45
    <h2>
    0.45
     vanity
    0.45
    ’,
    0.44
    <i>
    0.43
    POSITIVE LOGITS
     seguimiento
    0.52
     수준
    0.50
     sejumlah
    0.49
     विद्यार्थी
    0.49
     گاه
    0.49
     ਕਿਸ
    0.48
     उंची
    0.47
    seign
    0.47
     सीमा
    0.46
     चेक
    0.46
    Activations Density 0.000%

    No Known Activations