© 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. 110111
    Prev
    Next
    INDEX
    Explanations

    enter your

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

    approach differs or depends

    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
    Not in Any Lists

    No Comments

    Negative Logits
     I
    0.49
     P
    0.48
     beant
    0.48
     PAF
    0.48
     increased
    0.46
     emotional
    0.46
     Increased
    0.45
     paed
    0.45
     terapeut
    0.44
     fibromyalgia
    0.44
    POSITIVE LOGITS
     दिरहम
    0.51
    Imagen
    0.49
     הראשון
    0.48
    얗
    0.48
    🍢
    0.48
     цих
    0.47
     ገን
    0.46
     במ
    0.46
     шам
    0.46
     היי
    0.46
    Activations Density 0.000%

    No Known Activations