© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95681
    Prev
    Next
    INDEX
    Explanations

    recent events and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     You
    -2.56
    <
    -2.23
    ?
    -2.23
    ]
    -2.13
    %
    -2.06
    蟥
    -2.06
    <td>
    -2.00
    ."
    -1.99
    ו
    -1.95
    ).
    -1.91
    POSITIVE LOGITS
    
    2.45
    笮
    2.39
     notable
    2.19
    蒹
    2.19
     gewähr
    2.09
    鉨
    2.02
     vilja
    2.02
     developments
    1.98
    b
    1.98
     noteworthy
    1.96
    Activations Density 0.020%

    No Known Activations