© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104427
    Prev
    Next
    INDEX
    Explanations

    future action verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    explains scenarios and associated outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    も
    0.53
    יר
    0.48
    ната
    0.48
    Egyptian
    0.48
    Almost
    0.46
    シリーズ
    0.46
    ير
    0.46
     ARTICLES
    0.45
    га
    0.45
    點
    0.45
    POSITIVE LOGITS
     सीधे
    0.49
     पहन
    0.49
     आधे
    0.48
    hci
    0.47
     대비
    0.47
    nolds
    0.46
     컴퓨
    0.45
     Multiply
    0.45
    dió
    0.44
     BuildableName
    0.44
    Activations Density 0.002%

    No Known Activations