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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1685
    Prev
    Next
    INDEX
    Explanations

    quoted content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused10>
    0.70
    )$}
    0.66
    sic
    0.65
     Paryayvachi
    0.63
    annya
    0.63
    <unused3>
    0.62
    )}{
    0.62
    ătate
    0.61
    )}=
    0.60
    тивна
    0.60
    POSITIVE LOGITS
    '>";
    0.71
    ’
    0.66
    ㅋㅋㅋㅋ
    0.59
    -”
    0.59
     ㅋㅋ
    0.59
    การ
    0.58
    Is
    0.58
     कारोबार
    0.57
     이르
    0.57
    ”.
    0.56
    Activations Density 0.471%

    No Known Activations