© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2985
    Prev
    Next
    INDEX
    Explanations

    social role

    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
    fe
    0.46
    衤
    0.45
    and
    0.44
    気軽に
    0.44
    PC
    0.43
    ר
    0.43
    ad
    0.42
    FT
    0.42
    clas
    0.42
    it
    0.41
    POSITIVE LOGITS
     azione
    0.51
     distractions
    0.48
     LIABLE
    0.45
     ಅಮ
    0.45
     scelta
    0.45
     additives
    0.44
     entanglement
    0.44
    ꯌ
    0.43
     magia
    0.43
    態
    0.43
    Activations Density 0.001%

    No Known Activations