© 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. 192829
    Prev
    Next
    INDEX
    Explanations

    list items or descriptions

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

    specialized development and function

    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
    Sph
    0.43
    브
    0.41
    friend
    0.40
    陽
    0.39
    ambers
    0.38
    PS
    0.38
     neut
    0.38
     व्हाट
    0.38
    OfString
    0.37
    send
    0.37
    POSITIVE LOGITS
     convened
    0.47
     AHA
    0.47
     immunos
    0.46
     preprocessing
    0.46
     computationally
    0.46
    aménagement
    0.46
    𝜁
    0.46
     quantized
    0.46
     aumentare
    0.46
     partecipare
    0.45
    Activations Density 0.000%

    No Known Activations