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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 1646
    Prev
    Next
    INDEX
    Explanations

    sexually suggestive content

    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_53_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
     consecuencia
    0.42
     মূ
    0.39
    Medit
    0.38
    阠
    0.38
    ισμό
    0.38
    σό
    0.38
    !-
    0.36
    畈
    0.36
     segundos
    0.36
    مول
    0.36
    POSITIVE LOGITS
     implying
    0.49
     implied
    0.42
     adult
    0.42
     suggesting
    0.42
     imply
    0.41
     suggests
    0.39
     suggest
    0.38
     especially
    0.38
     nine
    0.38
    rob
    0.37
    Activations Density 0.018%

    No Known Activations