© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 14901
    Prev
    Next
    INDEX
    Explanations

    unwanted/harmful sexual behavior

    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_53_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
     Attitudes
    0.40
    Тре
    0.39
    𒀸
    0.38
    簱
    0.38
    ℤ
    0.37
     attitudes
    0.37
    ர்த்த
    0.37
     proclamation
    0.36
     reflects
    0.36
    ከና
    0.36
    POSITIVE LOGITS
    lab
    0.47
    xe
    0.43
    XE
    0.41
     হালকা
    0.40
    ix
    0.40
    xc
    0.40
     XC
    0.39
     McDaniel
    0.39
    insp
    0.39
    ξ
    0.38
    Activations Density 0.012%

    No Known Activations