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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7509
    Prev
    Next
    INDEX
    Explanations

    are you missing or trying to install

    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
     Рай
    -0.75
     бр
    -0.75
     socially
    -0.69
    使得
    -0.68
    歩道
    -0.68
    бр
    -0.66
    berlin
    -0.66
    אים
    -0.65
    amante
    -0.65
     Textbook
    -0.65
    POSITIVE LOGITS
    edes
    0.85
     aren
    0.84
     rosto
    0.81
    Campbell
    0.81
    Are
    0.80
    不仅
    0.79
     Stephenson
    0.78
    JsonProperty
    0.77
    脸
    0.76
    VIRTUAL
    0.75
    Activations Density 0.046%

    No Known Activations