© 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. 36814
    Prev
    Next
    INDEX
    Explanations

    copy and paste

    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
    蚂
    0.48
    ।
    0.45
    为
    0.45
    韦
    0.44
    wok
    0.44
    ciphertext
    0.43
    国产
    0.42
     произведения
    0.42
    ίνουν
    0.42
    器
    0.41
    POSITIVE LOGITS
     successivo
    0.50
     pele
    0.49
     mø
    0.49
     dura
    0.49
     homog
    0.49
     pola
    0.48
     pärast
    0.48
     varia
    0.47
     varie
    0.47
     oike
    0.47
    Activations Density 0.002%

    No Known Activations