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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8372
    Prev
    Next
    INDEX
    Explanations

    adding elements to collections

    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
    ;
    -1.16
    }$;
    -1.01
     from
    -0.84
     that
    -0.83
     since
    -0.82
     Since
    -0.82
    %;
    -0.75
    に着
    -0.74
     does
    -0.74
    中断
    -0.74
    POSITIVE LOGITS
    append
    1.63
    push
    1.60
     +=
    1.60
     append
    1.45
     push
    1.32
     PUSH
    1.31
    extend
    1.22
    [:]
    1.10
    PUSH
    1.06
     addObject
    1.05
    Activations Density 0.008%

    No Known Activations