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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148567
    Prev
    Next
    INDEX
    Explanations

    sexual activity, abuse, or interaction

    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_29_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
     –
    0.98
     যের
    0.84
     played
    0.82
    —
    0.81
    infrastructure
    0.81
     جس
    0.80
    ashop
    0.80
     источник
    0.79
    ﹙
    0.78
     […]
    0.78
    POSITIVE LOGITS
     souh
    0.85
     اكو
    0.81
    ább
    0.77
     convain
    0.75
    бавля
    0.74
    積極
    0.74
     acept
    0.74
     istraž
    0.72
     pins
    0.72
    ！！！
    0.71
    Activations Density 0.001%

    No Known Activations