© 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. 531
    Prev
    Next
    INDEX
    Explanations

    colors and descriptive adjectives

    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
    ">⁢</
    2.69
    GTUIKit
    2.64
    ExpNow
    2.59
     sConfig
    2.58
    Transicao
    2.48
     continueRoutine
    2.47
     órg
    2.47
    <unused1285>
    2.47
    Sebelum
    2.46
    okatokat
    2.46
    POSITIVE LOGITS
    headed
    2.04
    ness
    1.89
     colored
    1.87
    est
    1.86
    -
    1.82
    hearted
    1.82
     coloured
    1.74
    thorn
    1.67
    ish
    1.65
     hearted
    1.58
    Activations Density 4.479%

    No Known Activations