© 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. 31
    Prev
    Next
    INDEX
    Explanations

    lists ending in more

    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
    '
    1.65
    &#
    1.46
    #
    1.44
    R
    1.44
    公式サイト
    1.42
    вання
    1.39
    ini
    1.33
    Ex
    1.32
     completar
    1.32
    `
    1.31
    POSITIVE LOGITS
    竽
    1.50
    <unused1821>
    1.48
    <unused1231>
    1.45
    <unused1110>
    1.44
    <unused356>
    1.44
    㘿
    1.44
     ähm
    1.42
    <unused158>
    1.40
    <unused990>
    1.39
     પરંતુ
    1.38
    Activations Density 0.566%

    No Known Activations