© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5781
    Prev
    Next
    INDEX
    Explanations

    induce sexual arousal coercion

    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_22_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
     Attack
    0.75
    隕
    0.69
     Nodes
    0.66
     atk
    0.66
     apoyar
    0.66
     nodes
    0.66
    Attack
    0.64
     Saras
    0.64
    <0xE1>
    0.64
    Libra
    0.64
    POSITIVE LOGITS
     prisoners
    1.51
     prisoner
    1.46
     prison
    1.45
    Prison
    1.41
     prisons
    1.39
     detain
    1.36
     detainees
    1.35
     inmate
    1.34
     Prison
    1.34
    prison
    1.32
    Activations Density 0.369%

    No Known Activations