© 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. 20741
    Prev
    Next
    INDEX
    Explanations

    discussing death and stimulation

    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
    -
    0.50
     selbst
    0.46
    ěz
    0.46
    춰
    0.45
    ă
    0.44
     besser
    0.44
    ěž
    0.44
     dé
    0.44
    㱛
    0.43
     dragons
    0.43
    POSITIVE LOGITS
     horticulture
    0.47
    untamento
    0.42
     Bringing
    0.41
    ⿶
    0.40
     tasting
    0.39
     Uttar
    0.39
     tastings
    0.39
    ごと
    0.39
     Tasting
    0.38
     بنگالی
    0.38
    Activations Density 0.016%

    No Known Activations