© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14165
    Prev
    Next
    INDEX
    Explanations

    app component in code

    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_40_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
     භාවිත
    0.46
    AuthController
    0.42
    SaveChanges
    0.42
    welcome
    0.42
    Welcome
    0.41
    厈
    0.41
    addItem
    0.40
     welcome
    0.40
    ApiController
    0.39
    그러
    0.38
    POSITIVE LOGITS
     Malta
    0.39
     Maltese
    0.36
     luck
    0.35
    曾
    0.34
    డంలో
    0.34
     Faber
    0.34
     delay
    0.34
    plaat
    0.33
    кс
    0.33
     fudge
    0.33
    Activations Density 0.000%

    No Known Activations