© 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. 49245
    Prev
    Next
    INDEX
    Explanations

    由 Google DeepMind 训练

    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
     for
    0.49
     gpm
    0.40
     SQL
    0.40
    |+|
    0.39
    uo
    0.39
     Bitmap
    0.39
     Bridges
    0.39
     Constituency
    0.39
     nitrile
    0.38
     Quinta
    0.38
    POSITIVE LOGITS
    스크
    0.46
     கைது
    0.45
    ﺮ
    0.44
    ﻣ
    0.43
    𝘺
    0.42
    یکل
    0.41
     ہتھیار
    0.41
    х
    0.41
    ﻤ
    0.41
    стаў
    0.41
    Activations Density 0.002%

    No Known Activations