© 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. 28804
    Prev
    Next
    INDEX
    Explanations

    standard deviation, dilution, stem bleeding

    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
    ཋ
    0.41
     言っ
    0.41
    CHEMY
    0.39
    ANCES
    0.37
    ัล
    0.36
    שׁ
    0.36
    Encom
    0.35
    ErrorClazz
    0.35
    importanza
    0.35
    钀
    0.35
    POSITIVE LOGITS
    .
    0.41
     a
    0.40
    0.38
     the
    0.38
     is
    0.37
    ↵↵
    0.35
     semi
    0.35
    ,
    0.33
     https
    0.33
     Minister
    0.33
    Activations Density 0.083%

    No Known Activations