© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207329
    Prev
    Next
    INDEX
    Explanations

    use followed by verb

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

    duration before something happened

    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
    Negative Logits
     vetting
    0.44
     consecut
    0.43
     burgl
    0.43
    탠
    0.43
     pedicure
    0.42
     сопро
    0.42
     ventilators
    0.42
     Adrián
    0.42
     opcode
    0.41
     przepis
    0.40
    POSITIVE LOGITS
    )}$
    0.47
    ú
    0.47
    IN
    0.46
    hr
    0.46
    ROUND
    0.46
     *}\
    0.46
    insa
    0.46
    USTOM
    0.45
    ImagePath
    0.45
    chaos
    0.45
    Activations Density 0.000%

    No Known Activations