© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68567
    Prev
    Next
    INDEX
    Explanations

    emphasis markers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    -1.70
     on
    -1.69
     just
    -1.61
     for
    -1.55
     all
    -1.51
     only
    -1.51
     as
    -1.38
     not
    -1.38
     because
    -1.34
     with
    -1.31
    POSITIVE LOGITS
    <b>
    1.52
    </i>
    1.44
    '})
    1.39
    ]];
    1.37
    luft
    1.35
     kulinar
    1.34
    fär
    1.34
    '}}
    1.32
    folie
    1.29
     Dinas
    1.28
    Activations Density 0.003%

    No Known Activations