© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 729
    Prev
    Next
    INDEX
    Explanations

    economic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。.
    2.11
    .。
    1.95
    ।
    1.92
    ;.
    1.85
    。
    1.83
    。(
    1.73
    ।.
    1.72
    `.
    1.68
    ().
    1.67
    ।।
    1.64
    POSITIVE LOGITS
     isn
    1.54
     is
    1.43
    者は
    1.41
     అనేది
    1.37
     entails
    1.35
     involves
    1.33
    することは
    1.33
     equates
    1.29
     constitutes
    1.27
     would
    1.26
    Activations Density 2.914%

    No Known Activations