© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118917
    Prev
    Next
    INDEX
    Explanations

    according to

    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
     gmail
    -0.86
    ánto
    -0.82
    糬
    -0.81
     тук
    -0.80
    rhosis
    -0.79
     jacke
    -0.79
    ลด
    -0.79
     Económica
    -0.78
    imente
    -0.77
    结束后
    -0.77
    POSITIVE LOGITS
     source
    1.26
    source
    1.24
     Source
    1.23
    Source
    1.19
     according
    1.16
    sources
    1.13
    getSource
    1.08
     sources
    1.07
     Sources
    1.03
    Image
    1.02
    Activations Density 0.054%

    No Known Activations