© 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. 49244
    Prev
    Next
    INDEX
    Explanations

    positive and harmless

    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
    ל
    0.76
    }-
    0.70
    ula
    0.61
    Ä
    0.61
    Server
    0.58
    İ
    0.58
    ip
    0.57
    är
    0.57
    Were
    0.57
    ittees
    0.57
    POSITIVE LOGITS
     positive
    0.98
     positivo
    0.94
     Positive
    0.91
     positiva
    0.77
     pozitiv
    0.77
     negative
    0.76
     positivos
    0.75
     positivas
    0.75
    Positive
    0.72
     सकारात्मक
    0.72
    Activations Density 0.064%

    No Known Activations