© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1926
    Prev
    Next
    INDEX
    Explanations

    plush couches

    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_40_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
     bicarbon
    0.53
    렙
    0.52
     underage
    0.49
    alop
    0.49
    pets
    0.48
    acola
    0.48
    坦克
    0.46
    amit
    0.45
    _{\{
    0.45
     Bikes
    0.44
    POSITIVE LOGITS
    zus
    0.45
    )$-
    0.43
     remarkably
    0.42
    стин
    0.41
    дин
    0.40
     존
    0.40
    にご
    0.40
    ક્તિ
    0.40
    uy
    0.39
    ノ
    0.39
    Activations Density 0.002%

    No Known Activations