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. 152
    Prev
    Next
    INDEX
    Explanations

    code and timestamps

    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
     Garvey
    -0.77
    ¸
    -0.75
    lichting
    -0.68
    hdys
    -0.66
    hall
    -0.65
    thirty
    -0.65
     Ayala
    -0.65
     spos
    -0.65
    agger
    -0.65
    jø
    -0.65
    POSITIVE LOGITS
    ᗯ
    0.69
    ANNEL
    0.68
     Naj
    0.67
     aucune
    0.66
     Mir
    0.64
     replaceable
    0.64
    十大
    0.64
    rosa
    0.63
     ISP
    0.63
    AndFlush
    0.62
    Activations Density 0.065%

    No Known Activations