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. 7724
    Prev
    Next
    INDEX
    Explanations

    semicolons or other 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
     of
    -1.77
     to
    -1.64
     and
    -1.41
    ,
    -1.40
     for
    -1.35
    =[]
    
    -1.29
     recoge
    -1.26
     then
    -1.26
     in
    -1.23
    参考にして
    -1.23
    POSITIVE LOGITS
    ;
    7.84
    }$;
    4.25
    ;
    4.16
    ;
    
    4.06
    ();
    3.92
    ؛
    3.86
     [];
    3.86
    $;
    3.77
    %;
    3.72
    ];
    3.66
    Activations Density 0.965%

    No Known Activations