© 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. 7910
    Prev
    Next
    INDEX
    Explanations

    expert in a field

    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
     erfahren
    0.69
     Objekte
    0.67
    剂
    0.66
    s
    0.65
    ائنات
    0.64
    ጳ
    0.63
     Objekt
    0.63
     უფ
    0.62
    ött
    0.61
     prij
    0.61
    POSITIVE LOGITS
     opinión
    0.79
    砌
    0.67
     opin
    0.66
     opiniones
    0.66
    𝓶
    0.66
     мнение
    0.65
    领域的
    0.63
    Hãy
    0.63
     conclusiones
    0.61
    Opin
    0.61
    Activations Density 0.120%

    No Known Activations