© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1051
    Prev
    Next
    INDEX
    Explanations

    generating sexually suggestive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     therefore
    0.65
     that
    0.61
     أ
    0.54
    <code>
    0.53
     però
    0.53
    ம்
    0.52
    ı
    0.52
    о
    0.51
     accordingly
    0.50
     faz
    0.50
    POSITIVE LOGITS
    <unused1781>
    1.36
     geopolitical
    1.32
     sexual
    1.31
     기타
    1.28
    <unused162>
    1.28
    <unused399>
    1.28
    <unused1855>
    1.28
    <unused287>
    1.26
    <unused516>
    1.25
    𒐤
    1.25
    Activations Density 2.739%

    No Known Activations