© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24862
    Prev
    Next
    INDEX
    Explanations

    condoms and barrier protection

    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_all/layer_41_width_262k_l0_big
    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
    ាតុ
    0.49
     aggregate
    0.43
     âng
    0.42
     achromatic
    0.42
    ꯌ
    0.42
    াচ
    0.41
     lê
    0.41
    ﺑ
    0.41
     clustering
    0.40
    せる
    0.39
    POSITIVE LOGITS
     condoms
    1.27
     condom
    1.19
    Cond
    0.86
     Cond
    0.86
    cond
    0.75
     kond
    0.71
     contraception
    0.71
     HIV
    0.68
     Kond
    0.67
     contraceptive
    0.66
    Activations Density 0.005%

    No Known Activations