© 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. 146590
    Prev
    Next
    INDEX
    Explanations

    choice of words

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

    ancient China historical settlement

    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
    ually
    0.47
     cavities
    0.45
    ⅼ
    0.45
    icus
    0.44
    ically
    0.42
    ica
    0.42
    olar
    0.42
    ific
    0.41
    ides
    0.41
     Joh
    0.41
    POSITIVE LOGITS
    从来
    0.52
    Anybody
    0.48
     niemand
    0.48
    はん
    0.48
     kein
    0.47
    沈
    0.47
    ে
    0.47
     परेशानी
    0.45
    音频
    0.44
    Somebody
    0.44
    Activations Density 0.000%

    No Known Activations