© 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. 226582
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sel
    0.49
    straight
    0.46
    nid
    0.46
    8
    0.46
    opolitical
    0.46
    7
    0.46
     covers
    0.45
    legg
    0.45
    kn
    0.45
    sets
    0.44
    POSITIVE LOGITS
     prépuce
    0.46
     schönsten
    0.46
     паль
    0.44
    惮
    0.43
    ...\
    0.43
     પ્રેમ
    0.43
    Seqs
    0.43
     romanzo
    0.43
    잖아
    0.42
     резо
    0.42
    Activations Density 0.004%

    No Known Activations