© 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. 252437
    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
    彷
    0.48
     eer
    0.43
    AZIONE
    0.41
     perceptual
    0.41
     Toward
    0.41
     horrors
    0.40
    盯着
    0.40
     temper
    0.40
     menacing
    0.40
     homophobic
    0.40
    POSITIVE LOGITS
    clid
    0.51
    ılan
    0.50
    laş
    0.50
     işlemi
    0.47
    𝚖
    0.46
    otras
    0.46
    xa
    0.45
    س
    0.45
    utm
    0.45
    udu
    0.44
    Activations Density 0.001%

    No Known Activations