© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176370
    Prev
    Next
    INDEX
    Explanations

    From the

    np_acts-logits-general · gemini-2.5-flash-lite

    highlighting, speed, opportunity, overtake, no cooking, utility, keeps skiving, where to look, age, brutal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Network
    0.48
     Online
    0.48
     Oral
    0.48
     Configuring
    0.47
     Platform
    0.46
     Polarization
    0.46
     Even
    0.46
    آم
    0.45
     Football
    0.45
    茭
    0.45
    POSITIVE LOGITS
     taglio
    0.53
     reporte
    0.47
     caters
    0.46
     mereka
    0.46
    iry
    0.45
     theyre
    0.44
     che
    0.44
     uncut
    0.43
    ូង
    0.43
     they
    0.43
    Activations Density 0.001%

    No Known Activations