Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8675
    Prev
    Next
    INDEX
    Explanations

    closing code string punctuation

    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_34/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
     before
    -1.14
     but
    -1.05
     when
    -0.98
     ہے
    -0.98
    ;
    -0.96
    ];
    -0.96
     where
    -0.94
     Fußballspieler
    -0.94
     its
    -0.93
     Bestand
    -0.93
    POSITIVE LOGITS
    ").
    1.58
    ').
    1.53
    ”).
    1.06
     cabaña
    1.05
     %.
    1.03
     paysage
    0.97
    ).
    0.96
    ».
    0.95
    ,#
    0.95
    '].
    0.94
    Activations Density 0.015%

    No Known Activations