© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7056
    Prev
    Next
    INDEX
    Explanations

    security and identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     booze
    1.35
    charset
    1.32
     tequila
    1.30
     PERIOD
    1.29
     dolomite
    1.28
     tangy
    1.27
     calcite
    1.25
    )^{*
    1.24
     moeil
    1.22
     lingua
    1.22
    POSITIVE LOGITS
     Instrumented
    1.33
     occupant
    1.23
     aboard
    1.21
     头
    1.20
    Io
    1.17
     Injuries
    1.15
     casualties
    1.14
    Jou
    1.09
    casualties
    1.09
    ipede
    1.07
    Activations Density 0.051%

    No Known Activations