© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26548
    Prev
    Next
    INDEX
    Explanations

    machines, instruments, species, disorders

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

    nouns related to technical or professional objects, especially in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.31
     and
    -1.06
     отредакти
    -0.97
     it
    -0.96
    ");
    -0.92
    untamiento
    -0.91
    běh
    -0.90
    část
    -0.90
     this
    -0.89
    奚
    -0.88
    POSITIVE LOGITS
     نیز
    1.05
    푉
    0.93
     stockings
    0.89
     marketplaces
    0.89
    èle
    0.87
    Palazzo
    0.86
     enterprising
    0.85
    Andrzej
    0.85
    ﻷ
    0.84
    臼
    0.84
    Activations Density 0.081%

    No Known Activations