© 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
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4917
    Prev
    Next
    INDEX
    Explanations

    prime for, statement with, Database retrieval, most prominent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    .
    1.58
    ,
    1.43
     woe
    1.41
    iless
    1.33
     привы
    1.33
    遡
    1.32
     sebab
    1.30
    为此
    1.29
    cale
    1.23
    ese
    1.21
    POSITIVE LOGITS
    ₁
    1.58
    combined
    1.56
     komplett
    1.55
    GROUP
    1.47
     restant
    1.44
     categorized
    1.43
    INCLUDE
    1.43
     complemented
    1.43
     heartfelt
    1.42
    包含
    1.41
    Activations Density 0.067%

    No Known Activations