© 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. 246
    Prev
    Next
    INDEX
    Explanations

    connecting items or 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
    However
    1.99
    Pour
    1.76
    Priv
    1.67
    С
    1.65
     However
    1.61
    Most
    1.61
    In
    1.59
    After
    1.58
    ның
    1.57
    Take
    1.54
    POSITIVE LOGITS
    ंगाबाद
    3.52
    laquo
    2.89
    rogens
    2.61
    nbs
    2.52
    REW
    2.51
    ldquo
    2.47
    ndash
    2.43
    蔼
    2.35
    ROID
    2.32
    mdash
    2.29
    Activations Density 0.795%

    No Known Activations