© 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. 5722
    Prev
    Next
    INDEX
    Explanations

    express willingness to help

    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
    テイ
    1.66
     classific
    1.58
     stand
    1.57
    trong
    1.54
     tall
    1.54
    eton
    1.53
     座
    1.52
     score
    1.51
    座
    1.50
     Adapted
    1.49
    POSITIVE LOGITS
     INTERRUPTION
    1.34
    运转
    1.30
    ётся
    1.20
    Conversely
    1.20
    Backward
    1.20
     regioni
    1.19
    虧
    1.18
     therewith
    1.18
    atenated
    1.17
     endeavors
    1.17
    Activations Density 0.020%

    No Known Activations