© 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. 9436
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    ן
    2.25
    ра
    2.14
    ن
    1.98
    َهُ
    1.88
    раст
    1.87
    ત
    1.87
    َ
    1.80
    ре
    1.79
     puns
    1.79
    ر
    1.78
    POSITIVE LOGITS
    ی
    1.63
    ק
    1.58
     obliquely
    1.57
    a
    1.53
    ায়ের
    1.52
    oczy
    1.52
    others
    1.50
    ans
    1.49
    ti
    1.49
    c
    1.49
    Activations Density 0.026%

    No Known Activations