© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    how to start developing or managing

    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
    Negative Logits
    7
    1.68
    煖
    1.57
     nasc
    1.45
    6
    1.45
    8
    1.42
     vertu
    1.37
     Spawn
    1.37
     ανθ
    1.36
     intermedi
    1.34
    quetas
    1.34
    POSITIVE LOGITS
    딧
    2.23
     evidence
    2.11
    비를
    2.09
     itineraries
    2.03
     anaemia
    1.96
     ophthal
    1.94
     speeds
    1.92
     visited
    1.90
     floods
    1.88
     mussten
    1.88
    Activations Density 0.000%

    No Known Activations