© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168538
    Prev
    Next
    INDEX
    Explanations

    heck and hell

    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_40_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
     cunt
    0.40
     cruise
    0.39
     multiport
    0.39
    一点
    0.37
     Kant
    0.36
    Mam
    0.36
     eid
    0.36
    驥
    0.36
    πί
    0.35
     bullshit
    0.35
    POSITIVE LOGITS
     Heck
    0.44
    entially
    0.43
     heck
    0.41
    ulously
    0.40
    amalla
    0.40
    uya
    0.40
     ভালোভাবে
    0.40
    obbly
    0.40
    枷
    0.40
    abayashi
    0.39
    Activations Density 0.001%

    No Known Activations