© 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. 21339
    Prev
    Next
    INDEX
    Explanations

    test set

    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
    であり
    0.41
    浃
    0.39
     маршру
    0.38
     wewnętr
    0.37
     плюс
    0.37
    个性
    0.36
     буенча
    0.36
     东
    0.36
    进一步
    0.35
    AspNetCore
    0.35
    POSITIVE LOGITS
     unaffected
    0.61
     unin
    0.55
     Reference
    0.48
     non
    0.46
    Reference
    0.46
    non
    0.44
     reference
    0.44
    comparison
    0.44
    reference
    0.43
     Vergleich
    0.43
    Activations Density 0.056%

    No Known Activations