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. 8590
    Prev
    Next
    INDEX
    Explanations

    directions and navigation

    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
    estado
    -0.79
    BaseActivity
    -0.78
    uminazione
    -0.71
    łego
    -0.70
    economia
    -0.68
    ureau
    -0.67
    cartItems
    -0.66
    เยอะ
    -0.66
    Economia
    -0.66
     commemorative
    -0.65
    POSITIVE LOGITS
     directions
    1.64
    Directions
    1.58
    directions
    1.52
     Directions
    1.49
     nav
    1.23
     DIRECTIONS
    1.11
    nav
    1.05
     Nav
    1.04
     Direction
    1.02
     DIRECTION
    0.97
    Activations Density 0.007%

    No Known Activations