© 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. 1719
    Prev
    Next
    INDEX
    Explanations

    descriptive and vivid language that evokes atmosphere and character dynamics.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    describing people by 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
     bytes
    0.31
    R
    0.31
    a
    0.29
    S
    0.29
    L
    0.29
    is
    0.28
     metadata
    0.28
    to
    0.28
    bytes
    0.28
    C
    0.28
    POSITIVE LOGITS
     who
    0.49
     ktorí
    0.48
     الذين
    0.47
     kteří
    0.40
     extraordinaire
    0.40
     którzy
    0.39
     whose
    0.38
     जिन्होंने
    0.37
     quienes
    0.36
     quien
    0.36
    Activations Density 0.420%

    No Known Activations