© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4784
    Prev
    Next
    INDEX
    Explanations

    list items or headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     deficient
    1.30
     PMS
    1.27
    QUIS
    1.22
     NULL
    1.21
    厨
    1.18
    null
    1.17
    deficient
    1.17
    PMS
    1.16
    varnothing
    1.12
     _:
    1.11
    POSITIVE LOGITS
     والج
    1.06
    年に
    1.03
    沣
    1.02
     grandson
    0.98
    闔
    0.97
    erar
    0.96
    orrag
    0.94
     بإ
    0.92
    وبه
    0.91
    滦
    0.91
    Activations Density 0.033%

    No Known Activations