© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4707
    Prev
    Next
    INDEX
    Explanations

    closing braces and commas

    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_15_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
     бер
    2.50
    团
    2.44
    apply
    2.31
    轫
    2.30
     indywidual
    2.30
    throw
    2.30
    kinds
    2.28
    KAM
    2.28
    덬
    2.28
    HAB
    2.26
    POSITIVE LOGITS
    ubel
    0.80
    edly
    0.76
     peered
    0.75
     errand
    0.67
    arged
    0.66
     necessitated
    0.66
     alimenta
    0.64
    erum
    0.64
    mäßige
    0.63
     errands
    0.63
    Activations Density 0.000%

    No Known Activations