© 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-262K
    7. 71258
    Prev
    Next
    INDEX
    Explanations

    card, vanished, Questions, Limited, future, AUD

    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_262k_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
    Pixel
    0.51
    وأ
    0.51
    Rem
    0.50
    氛
    0.49
    akwa
    0.48
    Gesture
    0.46
    હ
    0.46
    Чи
    0.46
    PF
    0.45
    пол
    0.45
    POSITIVE LOGITS
     endpoints
    0.52
     shutt
    0.52
     nose
    0.51
     steaming
    0.50
     sacking
    0.50
     इसमें
    0.49
     ጣ
    0.49
     розподі
    0.49
     dressings
    0.48
     distributing
    0.48
    Activations Density 0.000%

    No Known Activations