© 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. 40-GEMMASCOPE-2-RES-262K
    7. 205047
    Prev
    Next
    INDEX
    Explanations

    sexualization of an object

    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
     انتظ
    0.50
    மிகு
    0.46
     മത്സര
    0.44
     Odd
    0.42
     Dominique
    0.42
    獵
    0.42
     Ord
    0.42
     Odysseus
    0.42
     erreurs
    0.41
    絬
    0.41
    POSITIVE LOGITS
    गण
    0.36
    stwo
    0.36
     yakin
    0.36
    ອກ
    0.35
    냔
    0.35
    hão
    0.34
    ByDefault
    0.34
     лично
    0.34
    ське
    0.34
    exion
    0.33
    Activations Density 0.000%

    No Known Activations