© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    section references followed by ')' or 'below'

    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
    庞
    0.47
    競技
    0.46
    schaft
    0.45
     മനുഷ്യ
    0.44
    ர்த்த
    0.43
    嗥
    0.42
    ورية
    0.42
     Hersteller
    0.42
    স্ব
    0.42
    לו
    0.42
    POSITIVE LOGITS
    ns
    0.44
     buradan
    0.44
    cks
    0.43
    q
    0.41
     longer
    0.40
    therefore
    0.40
    fa
    0.39
     repeatable
    0.39
    atán
    0.39
     quicker
    0.39
    Activations Density 0.030%

    No Known Activations