© 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. 5891
    Prev
    Next
    INDEX
    Explanations

    talk about or describe

    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
    padă
    0.44
     জে
    0.43
    {|
    0.43
    جام
    0.42
    冰
    0.42
    جلات
    0.42
     países
    0.42
    billing
    0.42
    㖪
    0.41
    解
    0.40
    POSITIVE LOGITS
    quelle
    0.53
     could
    0.52
    ang
    0.52
    σιν
    0.49
     automatically
    0.49
    could
    0.49
    herent
    0.48
    sworth
    0.47
     dürfte
    0.47
     wouldn
    0.46
    Activations Density 0.023%

    No Known Activations