© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8040
    Prev
    Next
    INDEX
    Explanations

    division problems solved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     примерно
    2.81
     setengah
    2.70
     quase
    2.69
    ань
    2.67
     особенно
    2.57
    꽤
    2.52
     vý
    2.51
     і
    2.48
     көп
    2.47
     praticamente
    2.47
    POSITIVE LOGITS
    levision
    1.15
    Majority
    1.15
     inorder
    1.11
     evidences
    1.08
    ‘’
    1.07
     asses
    1.02
     instrumentality
    0.91
    nection
    0.91
    andad
    0.91
     breadth
    0.90
    Activations Density 0.003%

    No Known Activations