© 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. 116654
    Prev
    Next
    INDEX
    Explanations

    person together

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

    Importantly, okay, car, link, key, thing

    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
    н
    0.49
    alternative
    0.48
    volunteer
    0.47
    Kristen
    0.47
     influenza
    0.46
    textArea
    0.46
    urban
    0.45
    Universität
    0.45
    Theatre
    0.45
     Zugang
    0.45
    POSITIVE LOGITS
     każdej
    0.51
    盼
    0.49
    买了
    0.46
     Because
    0.45
     inutil
    0.44
     dinero
    0.44
     Marx
    0.43
     hijo
    0.43
     But
    0.42
    可惜
    0.42
    Activations Density 0.001%

    No Known Activations