© 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. 14218
    Prev
    Next
    INDEX
    Explanations

    world

    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
    vvvert
    2.22
    𝘃
    2.16
    Consentiti
    2.16
    <unused1736>
    2.15
    眇
    2.13
    <unused358>
    2.12
    ꘏
    2.10
     _$_
    2.09
    OutOfBounds
    2.07
    <unused1846>
    2.06
    POSITIVE LOGITS
     pen
    1.29
    '
    1.27
    <b>
    1.27
     dai
    1.26
     per
    1.24
     dar
    1.23
    re
    1.22
    人民
    1.21
    "
    1.20
     care
    1.19
    Activations Density 0.000%

    No Known Activations