© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10054
    Prev
    Next
    INDEX
    Explanations

    genital terms, penis, genitalia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    н
    1.94
     NONINFRINGEMENT
    1.93
    fifths
    1.93
    widehat
    1.88
     %@
    1.87
    ⦕
    1.86
    Featuring
    1.77
     culminates
    1.77
     culminating
    1.76
     Gonzalo
    1.74
    POSITIVE LOGITS
    om
    1.99
    و
    1.87
    ین
    1.80
     строение
    1.71
    Returned
    1.68
    acje
    1.64
    其
    1.59
    ated
    1.58
    ান্তরিত
    1.56
    onyl
    1.56
    Activations Density 0.059%

    No Known Activations