© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27692
    Prev
    Next
    INDEX
    Explanations

    positive or negative states

    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
    🗡
    0.47
    frü
    0.46
     CCN
    0.46
     metaphysical
    0.45
    ccnc
    0.44
    🔪
    0.44
     schönsten
    0.44
    要注意
    0.44
    ="#{
    0.43
     OCLC
    0.43
    POSITIVE LOGITS
    ó
    0.46
    at
    0.45
     konsumen
    0.44
     बचत
    0.43
     Bă
    0.42
     расходов
    0.40
     didn
    0.39
     scoot
    0.39
    took
    0.39
    женный
    0.39
    Activations Density 0.001%

    No Known Activations