© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2556
    Prev
    Next
    INDEX
    Explanations

    cannabis, cannibal, Kannada

    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
    excluding
    0.40
     afloat
    0.40
     excluding
    0.39
    뢨
    0.39
    বৃন্দ
    0.39
     successors
    0.38
    烨
    0.38
    തിൽ
    0.37
    *_
    0.37
     userdata
    0.37
    POSITIVE LOGITS
     cannab
    0.50
     Cann
    0.50
     cann
    0.49
     cannibal
    0.49
    cann
    0.47
    Cann
    0.47
    abis
    0.46
    Kann
    0.44
     bist
    0.42
     kann
    0.40
    Activations Density 0.002%

    No Known Activations