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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7931
    Prev
    Next
    INDEX
    Explanations

    cheat, Related Links, This blog, A video, When Spring

    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
     rosas
    -1.03
     higien
    -0.95
    ріш
    -0.91
     demurrer
    -0.89
    rzez
    -0.89
    ähn
    -0.88
    年に
    -0.88
    НОЙ
    -0.87
     VOOR
    -0.85
     dátum
    -0.85
    POSITIVE LOGITS
     -
    1.29
    HexString
    1.00
    –
    0.93
    u
    0.89
    K
    0.88
    :
    0.88
    um
    0.88
    }-\
    0.87
     –
    0.86
    p
    0.86
    Activations Density 0.008%

    No Known Activations