© 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. 47099
    Prev
    Next
    INDEX
    Explanations

    specific filters

    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
    ق
    0.45
     Beau
    0.44
    鸬
    0.44
    роваться
    0.42
    工作人员
    0.42
     Стаўкі
    0.42
     نه
    0.41
     pratiquer
    0.41
     máxima
    0.41
    跺
    0.41
    POSITIVE LOGITS
    salad
    0.53
    gi
    0.52
     salad
    0.51
    ni
    0.49
    new
    0.48
    feast
    0.47
    iname
    0.47
    ch
    0.47
    name
    0.46
    label
    0.44
    Activations Density 0.001%

    No Known Activations