© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16224
    Prev
    Next
    INDEX
    Explanations

    numbers and letters, like `(e.g., U-100, U-200, U-300)`

    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
    இந்த
    0.76
     რუს
    0.75
     কাজেই
    0.74
    сол
    0.73
    ार
    0.72
    ال
    0.70
    お
    0.69
    م
    0.69
    にかけて
    0.68
     অবাধ
    0.67
    POSITIVE LOGITS
     buckles
    0.70
    pkins
    0.67
     insurgents
    0.60
     annuities
    0.60
     acidified
    0.59
     Gayatri
    0.59
    uña
    0.58
    附
    0.58
     Gujar
    0.58
     occident
    0.58
    Activations Density 0.105%

    No Known Activations