© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129697
    Prev
    Next
    INDEX
    Explanations

    media contexts

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

    media roles and activities

    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
    Negative Logits
    el
    1.16
    los
    0.84
    p
    0.83
    l
    0.82
    в
    0.79
    in
    0.79
    läuft
    0.79
    lation
    0.78
    jší
    0.77
    ون
    0.75
    POSITIVE LOGITS
    ς
    1.10
    s
    1.07
    ]
    1.07
    ;
    1.00
    }
    0.99
    <0x80>
    0.98
    (
    0.94
     जिसका
    0.91
    ی
    0.89
    سازی
    0.86
    Activations Density 0.025%

    No Known Activations