© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 685
    Prev
    Next
    INDEX
    Explanations

    found everywhere

    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_13_width_65k_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
    -
    0.78
    all
    0.67
     out
    0.65
    out
    0.65
    :
    0.63
     of
    0.62
    unt
    0.62
     to
    0.62
    ’
    0.61
    '
    0.61
    POSITIVE LOGITS
    𒉈
    1.10
    𒈲
    1.10
    𒈩
    1.09
    𒅅
    1.07
    𒀝
    1.07
    𒂠
    1.07
    𒅕
    1.07
    ⮃
    1.07
     ज़कात
    1.06
    ꗗ
    1.06
    Activations Density 1.373%

    No Known Activations