© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250268
    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
    we
    0.41
    p
    0.41
    ﻦ
    0.39
     تقویت
    0.38
    ᖃ
    0.37
     coerced
    0.36
     honed
    0.36
    性は
    0.36
     disenfranch
    0.36
    than
    0.36
    POSITIVE LOGITS
    嵬
    0.55
    },
    0.51
    ăl
    0.49
     Benutzer
    0.49
    이버
    0.48
     Elektrokhimiya
    0.46
    ;}
    0.46
     Assemble
    0.44
    strange
    0.44
     Categories
    0.44
    Activations Density 0.002%

    No Known Activations