© 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. 148905
    Prev
    Next
    INDEX
    Explanations

    how to use

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

    Past Medical History

    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
     Operator
    0.51
     operador
    0.47
     Operators
    0.46
     Minority
    0.45
     Currents
    0.45
     operat
    0.45
    ।
    0.45
     Cinemas
    0.45
    萠
    0.44
     wildflower
    0.44
    POSITIVE LOGITS
    banks
    0.50
    ('')
    0.48
     एकमे
    0.47
    udges
    0.46
    ication
    0.46
     چه
    0.46
    ຈະ
    0.45
     onward
    0.45
     emphasises
    0.45
    lipped
    0.44
    Activations Density 0.002%

    No Known Activations