© 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. 82784
    Prev
    Next
    INDEX
    Explanations

    rise, run, termination, minimalistic, dead

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

    what it is

    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
     cérémon
    0.58
     Tät
    0.51
     Sekret
    0.49
    ég
    0.48
     Aub
    0.48
     Präsident
    0.48
     Už
    0.46
     സാധ
    0.46
     Malgré
    0.45
     Ν
    0.45
    POSITIVE LOGITS
    minded
    0.50
    िन
    0.49
    :[/
    0.45
    vie
    0.44
    ue
    0.43
    splunk
    0.43
    lans
    0.42
     juncture
    0.42
     отношение
    0.42
     лицен
    0.42
    Activations Density 0.000%

    No Known Activations