© 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. 5502
    Prev
    Next
    INDEX
    Explanations

    helpful list

    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
    弛
    1.51
    луб
    1.49
    繰
    1.46
     сцене
    1.38
    slut
    1.36
     crossovers
    1.34
    比べて
    1.33
    厢
    1.31
     juxtaposition
    1.31
     unpredict
    1.29
    POSITIVE LOGITS
     Helps
    2.42
    helps
    2.13
    help
    2.13
     Helped
    2.03
     help
    2.01
     ajuda
    1.98
     aids
    1.96
    HELP
    1.96
     giúp
    1.93
     ajud
    1.92
    Activations Density 0.104%

    No Known Activations