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. 40-GEMMASCOPE-2-RES-262K
    4. 119653
    Prev
    Next
    INDEX
    Explanations

    often associated with harmful

    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_40_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
     Yadav
    0.40
     temática
    0.38
    Somebody
    0.38
     entrevista
    0.38
     répondre
    0.38
     verfü
    0.37
     FIVE
    0.36
    詁
    0.36
     réaliser
    0.36
     retros
    0.35
    POSITIVE LOGITS
     होकर
    0.45
    agnar
    0.39
     नव्हते
    0.39
     befri
    0.39
     концов
    0.38
     exiled
    0.38
    ankton
    0.37
    ippi
    0.37
    entieth
    0.36
    твори
    0.36
    Activations Density 0.000%

    No Known Activations