© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6294
    Prev
    Next
    INDEX
    Explanations

    table headers and descriptive labels

    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
    ◦
    1.88
     tennis
    1.80
     Facilit
    1.74
     rugby
    1.73
    basketball
    1.72
     negotiating
    1.72
    baseball
    1.71
     Passive
    1.68
    passive
    1.67
     passive
    1.67
    POSITIVE LOGITS
    ichtig
    1.43
     --------------
    1.39
    لسل
    1.33
    iranje
    1.31
    ină
    1.30
    となった
    1.29
     -------------
    1.28
    ณ์
    1.27
     loko
    1.27
     lucru
    1.26
    Activations Density 0.001%

    No Known Activations