© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 10514
    Prev
    Next
    INDEX
    Explanations

    names of people, companions, or terms of endearment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     r
    0.55
     Commander
    0.54
     cowardly
    0.54
     unstable
    0.53
     beaut
    0.52
     Harus
    0.52
     dumbbell
    0.52
     d
    0.51
     lender
    0.51
     commander
    0.50
    POSITIVE LOGITS
     ചോദ്യ
    0.65
    esia
    0.60
    तो
    0.58
    ؔ
    0.58
    撾
    0.57
    ológica
    0.56
    我
    0.56
    ﷺ
    0.56
     мы
    0.56
    quite
    0.56
    Activations Density 0.002%

    No Known Activations