© 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. 7660
    Prev
    Next
    INDEX
    Explanations

    zero, 0, inflation, percent

    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
    Вы
    0.59
     ибо
    0.59
    get
    0.57
    ments
    0.54
    >=
    0.54
    嶼
    0.54
    beam
    0.53
     obwohl
    0.53
    की
    0.53
    guh
    0.53
    POSITIVE LOGITS
     ZERO
    0.73
     zero
    0.67
     inflation
    0.66
    零
    0.66
     परसेंट
    0.63
     inflación
    0.63
     percent
    0.61
     Zero
    0.61
     willpower
    0.60
     calories
    0.60
    Activations Density 0.119%

    No Known Activations