© 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. 182572
    Prev
    Next
    INDEX
    Explanations

    Determining the best following word

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

    educational and exploration scenarios

    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
     carbohydrates
    0.46
    नहीं
    0.43
     femora
    0.43
    を有する
    0.43
    uées
    0.42
    ７
    0.42
    锗
    0.42
     ప్ర
    0.42
    spannung
    0.42
    currentChar
    0.41
    POSITIVE LOGITS
     MEC
    0.51
     quedando
    0.50
     FE
    0.49
     Determining
    0.48
     Ian
    0.46
     Thomson
    0.45
     Disaster
    0.45
     Hanson
    0.45
     Because
    0.45
    ä
    0.45
    Activations Density 0.000%

    No Known Activations