© 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. 973
    Prev
    Next
    INDEX
    Explanations

    sentiment positive or negative

    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
     tela
    0.21
     courants
    0.21
     quand
    0.21
     superficial
    0.21
     parec
    0.20
     atrib
    0.20
     ，
    0.19
     ifades
    0.19
     tiz
    0.19
     gener
    0.19
    POSITIVE LOGITS
     on
    0.25
    ㄽ
    0.23
    U
    0.23
     Бушлай
    0.22
    職員
    0.22
     त्यांना
    0.22
    W
    0.22
    Ф
    0.22
    on
    0.22
    Т
    0.21
    Activations Density 0.003%

    No Known Activations