© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110454
    Prev
    Next
    INDEX
    Explanations

    date and location details

    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
    砵
    -0.75
     Cassius
    -0.73
     Huo
    -0.73
    acken
    -0.72
     wysy
    -0.71
    Duane
    -0.70
     przecież
    -0.70
     Guatem
    -0.69
    隸
    -0.69
    yeli
    -0.68
    POSITIVE LOGITS
     UAE
    1.61
     Dubai
    1.49
    UAE
    1.40
     Sharjah
    1.27
     Hacker
    1.25
    GCC
    1.20
    Dubai
    1.17
     Emirates
    1.16
     GCC
    1.14
    fptr
    1.13
    Activations Density 0.010%

    No Known Activations