© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6429
    Prev
    Next
    INDEX
    Explanations

    assumptions and improvements made

    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
    assadors
    2.03
    bergement
    1.95
    quia
    1.92
    usters
    1.86
    azine
    1.85
    uster
    1.84
    epub
    1.84
    牘
    1.80
    isał
    1.79
    REAT
    1.77
    POSITIVE LOGITS
     Made
    1.74
    Made
    1.59
     MADE
    1.44
     made
    1.28
    made
    1.24
     responsibility
    1.24
     preparation
    1.18
    Preparation
    1.18
     Preparation
    1.17
     Make
    1.17
    Activations Density 0.070%

    No Known Activations