© 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. 71051
    Prev
    Next
    INDEX
    Explanations

    modelrelated to specific actions and states

    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
     estrat
    0.47
    崞
    0.46
     ftp
    0.44
     Oxidation
    0.44
    म
    0.44
     sham
    0.43
     diction
    0.43
     eas
    0.42
     allev
    0.42
     into
    0.41
    POSITIVE LOGITS
    ful
    0.50
    shit
    0.50
    γράφ
    0.50
    ytuc
    0.50
    ileen
    0.49
    摁
    0.49
    constrained
    0.48
    ków
    0.48
    amię
    0.48
    đen
    0.47
    Activations Density 0.006%

    No Known Activations