© 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. 27599
    Prev
    Next
    INDEX
    Explanations

    occupational, occult, or occipital variations

    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
     कु
    0.43
    hæng
    0.40
    を進
    0.39
     سیک
    0.38
    ർഡ്
    0.37
    bard
    0.36
    Ռ
    0.36
    рифмети
    0.35
    ियां
    0.35
    職
    0.35
    POSITIVE LOGITS
     OCC
    0.67
     Oc
    0.66
     Occupational
    0.63
     Occ
    0.63
    Occup
    0.61
     occ
    0.61
     Occup
    0.61
     oc
    0.59
     Occupation
    0.59
    asionally
    0.59
    Activations Density 0.009%

    No Known Activations