Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16458
    Prev
    Next
    INDEX
    Explanations

    deceptive or threatening solicitation

    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
    managerpage
    0.43
     SharePoint
    0.42
     минима
    0.42
     routine
    0.40
     ফ্র
    0.40
    新人
    0.40
     minimale
    0.40
    鑄
    0.39
     سریال
    0.38
     Variability
    0.38
    POSITIVE LOGITS
    ugian
    0.50
     Contrary
    0.43
     wilfully
    0.41
    usa
    0.40
     willfully
    0.40
    upid
    0.40
     willful
    0.40
    angering
    0.40
    adamente
    0.39
     persever
    0.38
    Activations Density 0.008%

    No Known Activations