© 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-65K
    7. 14471
    Prev
    Next
    INDEX
    Explanations

    sql auto_increment primary keys

    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_65k_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
     memastikan
    0.52
     diariamente
    0.46
    ю
    0.44
     indes
    0.42
     í
    0.42
     diferentes
    0.42
     matin
    0.42
    È
    0.42
     inseg
    0.41
    ène
    0.41
    POSITIVE LOGITS
    ,’”
    0.38
     Pear
    0.37
     নয়
    0.37
     čty
    0.36
    ادي
    0.36
    寘
    0.35
    polish
    0.35
    礬
    0.35
     নয়
    0.35
    两人
    0.34
    Activations Density 0.000%

    No Known Activations