© 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. 7320
    Prev
    Next
    INDEX
    Explanations

    Mahsa Amini

    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
     सैकड़ों
    0.64
     parallels
    0.64
    여
    0.63
    くる
    0.61
     paralelas
    0.57
    transit
    0.57
     Rutland
    0.56
     принципе
    0.54
     हजारों
    0.53
    ză
    0.53
    POSITIVE LOGITS
    rmann
    0.68
    seen
    0.67
     PAH
    0.66
     CHO
    0.63
    ্
    0.61
    ahaha
    0.60
    ölt
    0.60
    ത്യാ
    0.58
    kampf
    0.58
    ollow
    0.57
    Activations Density 0.221%

    No Known Activations