© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1639
    Prev
    Next
    INDEX
    Explanations

    Python code examples

    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_31_width_16k_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
    ạ
    0.73
    CTION
    0.70
    ं
    0.70
     차지
    0.68
    ש
    0.68
    Лі
    0.67
     ರ
    0.67
     phir
    0.66
    ن
    0.66
    trasound
    0.65
    POSITIVE LOGITS
     Rolle
    0.68
    alchemy
    0.64
    otheby
    0.61
     politiques
    0.59
    icle
    0.58
     actores
    0.58
     sostenible
    0.58
     biodiversity
    0.57
    logos
    0.57
    版本的
    0.57
    Activations Density 0.004%

    No Known Activations