© 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. 17256
    Prev
    Next
    INDEX
    Explanations

    black nodes or relationships

    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
    א
    0.55
    ﾒ
    0.50
     INSPE
    0.50
    ק
    0.48
    مو
    0.48
    கே
    0.47
    лица
    0.47
    メ
    0.45
     বো
    0.45
    ﻭ
    0.45
    POSITIVE LOGITS
     $
    0.52
     $(
    0.50
     tribut
    0.48
     hyp
    0.47
     luxury
    0.46
     tram
    0.45
     p
    0.45
     .
    0.44
    ing
    0.44
    '
    0.44
    Activations Density 0.004%

    No Known Activations