© 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-262K
    7. 135334
    Prev
    Next
    INDEX
    Explanations

    based solely on

    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_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
    f
    0.60
    z
    0.59
    1
    0.57
    0
    0.55
    b
    0.54
    a
    0.53
    _
    0.52
    con
    0.52
    re
    0.51
    de
    0.51
    POSITIVE LOGITS
    䓶
    0.52
    屜
    0.50
    䩕
    0.49
    篂
    0.49
     basée
    0.48
     현재
    0.47
     xhr
    0.46
     combinaison
    0.46
     പോലുള്ള
    0.46
     коюм
    0.46
    Activations Density 0.003%

    No Known Activations