© 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. 66166
    Prev
    Next
    INDEX
    Explanations

    creates backup

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

    precision and necessity

    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
     interviewed
    0.43
    らん
    0.41
     підви
    0.40
     unemployed
    0.39
     ?>
    0.39
     promptly
    0.39
    =[],
    0.39
    ?>
    0.38
    ()?>
    0.38
    跳转
    0.38
    POSITIVE LOGITS
     scrotum
    0.50
    愴
    0.50
     reality
    0.47
    鬓
    0.45
    drig
    0.45
     laboratorium
    0.45
     gren
    0.44
     platter
    0.44
    reality
    0.44
     accuracy
    0.44
    Activations Density 0.000%

    No Known Activations