© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3144
    Prev
    Next
    INDEX
    Explanations

    repeat or reoccurrence

    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_16_width_65k_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
    ä
    0.78
    _
    0.71
    ע
    0.65
     impulsar
    0.63
     moistur
    0.61
     ήταν
    0.60
     extruder
    0.58
     arth
    0.58
     impregnation
    0.58
    ing
    0.57
    POSITIVE LOGITS
    số
    0.80
    n
    0.79
    y
    0.77
    ni
    0.75
    на
    0.74
    l
    0.73
    在
    0.71
    る
    0.71
    number
    0.69
    squareup
    0.67
    Activations Density 0.298%

    No Known Activations