© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10173
    Prev
    Next
    INDEX
    Explanations

    fetishistic sexualization

    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_31_width_65k_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
    profit
    0.45
     heterocyclic
    0.41
    passive
    0.39
     sapiens
    0.38
    🗯
    0.38
     quercetin
    0.38
     voda
    0.38
    signup
    0.37
     is
    0.37
    ᆭ
    0.37
    POSITIVE LOGITS
    getMetering
    0.47
     Instrumental
    0.45
    лады
    0.44
     оказывается
    0.44
    ल
    0.44
    强大的
    0.43
    мпа
    0.43
    сті
    0.43
    实验室
    0.42
    ラブ
    0.42
    Activations Density 0.009%

    No Known Activations