© 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. 31-GEMMASCOPE-2-RES-262K
    7. 127483
    Prev
    Next
    INDEX
    Explanations

    qualities and categories

    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_31_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
    ##
    0.47
    actions
    0.47
    beans
    0.43
    ###
    0.41
    ↵↵
    0.41
    com
    0.38
     &
    0.37
     Actions
    0.37
    ](
    0.37
    ]]]]
    0.37
    POSITIVE LOGITS
     memoir
    0.47
     kitabı
    0.46
     miesią
    0.46
     Perempuan
    0.45
    lastCursor
    0.45
     melodrama
    0.45
    avacak
    0.45
    ruciating
    0.45
     siècles
    0.45
    鲞
    0.45
    Activations Density 0.010%

    No Known Activations