© 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. 185250
    Prev
    Next
    INDEX
    Explanations

    words followed by specific completions

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

    Emperor, future, relativity, adapters

    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
    dì
    0.45
    ník
    0.44
    liel
    0.44
     fanciful
    0.43
     券
    0.43
     এলো
    0.42
     Computed
    0.42
     найд
    0.42
     انگلیسی
    0.42
    }({\
    0.42
    POSITIVE LOGITS
    性
    0.52
     my
    0.51
    我
    0.51
     моём
    0.50
     Maver
    0.49
    S
    0.49
    Ronald
    0.47
    Gregory
    0.47
    一些
    0.46
     наши
    0.46
    Activations Density 0.000%

    No Known Activations