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. 134
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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
    bildet
    -0.84
    آخر
    -0.83
     Universidades
    -0.82
     oblic
    -0.82
    nations
    -0.78
     khảo
    -0.78
     Lester
    -0.77
    shapes
    -0.77
     Portage
    -0.77
     régiment
    -0.77
    POSITIVE LOGITS
    (
    0.82
     fraught
    0.79
    }(\
    0.71
    rod
    0.69
     レー
    0.68
     ruined
    0.68
     doskon
    0.68
     sufficiently
    0.67
    INTRODU
    0.67
     efforts
    0.67
    Activations Density 0.006%

    No Known Activations