© 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. 12-GEMMASCOPE-2-RES-16K
    7. 9422
    Prev
    Next
    INDEX
    Explanations

    pitbull

    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_12_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
    ס
    0.88
     المت
    0.82
     يت
    0.82
     startup
    0.79
     बढ़कर
    0.77
    Portug
    0.77
     দায়িত্ব
    0.77
     ي
    0.76
     های
    0.76
    ن
    0.76
    POSITIVE LOGITS
     mesons
    0.86
     betracht
    0.84
    %%%%%%%%%%%%%%%%
    0.82
    inderung
    0.81
    મ્
    0.80
     recited
    0.79
     FUNDS
    0.79
     erscheinen
    0.78
     infliction
    0.77
    ુ
    0.75
    Activations Density 0.000%

    No Known Activations