© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 503
    Prev
    Next
    INDEX
    Explanations

    complex or technical 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_7_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
    htra
    1.73
    ක
    1.68
     sueños
    1.66
    ւ
    1.63
    seg
    1.63
     nouveau
    1.55
    nius
    1.54
    ობაში
    1.54
    slf
    1.53
     hearts
    1.53
    POSITIVE LOGITS
    enapi
    1.62
    ुभ
    1.55
    нуться
    1.53
    erende
    1.53
    пону
    1.51
    াইট
    1.51
     نفسها
    1.50
    囿
    1.49
    ylob
    1.48
    对称
    1.46
    Activations Density 0.000%

    No Known Activations