© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78989
    Prev
    Next
    INDEX
    Explanations

    AI, image, cultural touchstone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    d
    0.57
     troughs
    0.48
    a
    0.44
    meng
    0.44
     Canvas
    0.43
     Ly
    0.43
     trophies
    0.42
     Pyaar
    0.41
     keyst
    0.41
     standings
    0.41
    POSITIVE LOGITS
    ším
    0.56
     spécifique
    0.49
    ᙱ
    0.45
    ذي
    0.44
    ematic
    0.44
     பிரச்சன
    0.44
    推進
    0.44
    的三
    0.43
     ምግብ
    0.43
     valable
    0.43
    Activations Density 0.002%

    No Known Activations