© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11665
    Prev
    Next
    INDEX
    Explanations

    past perfect tense indicator

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

    instructions or requirements

    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_40_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
    y
    0.76
    $,
    0.75
    s
    0.72
    ों
    0.72
    ς
    0.68
    k
    0.66
    rines
    0.65
    indeed
    0.63
    m
    0.63
    the
    0.61
    POSITIVE LOGITS
     been
    1.14
    been
    1.08
     Been
    1.07
    Been
    1.05
     BEEN
    0.89
     ollut
    0.77
     gotta
    0.69
     got
    0.64
     vært
    0.63
     olnud
    0.61
    Activations Density 0.519%

    No Known Activations