© 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. 10107
    Prev
    Next
    INDEX
    Explanations

    hundreds or thousands

    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
    ts
    2.02
    ter
    1.92
    a
    1.88
    ти
    1.75
    си
    1.72
    ss
    1.60
    taining
    1.60
    ו
    1.56
    ru
    1.52
    this
    1.52
    POSITIVE LOGITS
    BURG
    1.70
     impenetr
    1.68
     thousands
    1.65
     hundreds
    1.63
     milliers
    1.56
    ED
    1.54
     undertake
    1.48
     minuten
    1.47
     nCmdShow
    1.47
     levied
    1.46
    Activations Density 0.082%

    No Known Activations