© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 8630
    Prev
    Next
    INDEX
    Explanations

    quoted introductions

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ended
    0.83
    o
    0.80
    a
    0.80
    as
    0.78
    _),
    0.76
    et
    0.75
    ends
    0.72
    y
    0.72
    _,
    0.70
    rogen
    0.70
    POSITIVE LOGITS
    .'”
    1.12
    ……”
    1.02
    Whether
    1.01
    Often
    1.01
    ’”
    1.00
    Governance
    0.99
    Conj
    0.97
    Produ
    0.97
     Gestión
    0.97
    Lorsque
    0.97
    Activations Density 0.076%

    No Known Activations