© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8747
    Prev
    Next
    INDEX
    Explanations

    abuse, exploitation, sexual violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     slicing
    0.80
     trimming
    0.79
     biodegradable
    0.79
     bland
    0.77
     knack
    0.74
     slic
    0.73
     two
    0.73
    '
    0.72
     plug
    0.72
     trimmed
    0.72
    POSITIVE LOGITS
    ulnerable
    0.97
     adolescents
    0.95
     নিপী
    0.93
     homelessness
    0.92
     নির্যাতন
    0.91
    伤害
    0.88
    虐
    0.87
    aternal
    0.86
     violencia
    0.86
     vulnerabilities
    0.85
    Activations Density 0.017%

    No Known Activations