© 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. 133605
    Prev
    Next
    INDEX
    Explanations

    Someone followed by a verb

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

    someone plus action

    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
    d
    0.80
    in
    0.77
    rs
    0.71
    a
    0.71
    rl
    0.70
    p
    0.67
    es
    0.66
    ll
    0.66
    ك
    0.65
    square
    0.63
    POSITIVE LOGITS
    л
    0.98
    Someone
    0.76
     Someone
    0.75
     iemand
    0.69
     quelqu
    0.66
     alguien
    0.64
    ве
    0.64
     alguém
    0.62
    вере
    0.59
     jemand
    0.59
    Activations Density 0.066%

    No Known Activations