© 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. 111494
    Prev
    Next
    INDEX
    Explanations

    Exploitation of Characters

    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
     للغاية
    0.47
    未必
    0.46
    にも
    0.46
     可能
    0.45
    tements
    0.44
     اسے
    0.44
    蹂
    0.43
    ವನ್ನು
    0.43
     المعروف
    0.42
    Gesch
    0.42
    POSITIVE LOGITS
    0
    0.54
    9
    0.50
    5
    0.49
    J
    0.48
    6
    0.47
     COR
    0.46
    8
    0.46
     Programa
    0.45
    O
    0.45
    go
    0.45
    Activations Density 0.011%

    No Known Activations