© 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. 138118
    Prev
    Next
    INDEX
    Explanations

    contractions followed by verbs

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

    CPU bottleneck, mortgages, Pewter

    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
     is
    0.45
     )
    0.44
    )
    0.44
    ↵↵
    0.43
    )},
    0.43
    }></
    0.42
    xD
    0.41
    `
    0.41
    ﻙ
    0.41
    HP
    0.40
    POSITIVE LOGITS
     لحظ
    0.54
     информацией
    0.51
     multitudes
    0.50
     следующий
    0.49
     glimpses
    0.49
     keenly
    0.48
     matchups
    0.48
     Almanac
    0.48
     получите
    0.48
     логи
    0.48
    Activations Density 0.001%

    No Known Activations