© 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. 10-GEMMASCOPE-RES-131K
    7. 59599
    Prev
    Next
    INDEX
    Explanations

    bandit, outlaw, banished, brig, smugglers

    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_10/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
     =
    -2.92
     sprüche
    -2.86
    a
    -2.67
    ઁ
    -2.47
    on
    -2.38
    ﺅ
    -2.27
     españ
    -2.27
    полне
    -2.23
    an
    -2.22
     Inſ
    -2.20
    POSITIVE LOGITS
    </b>
    2.58
     если
    2.31
     améli
    2.30
     If
    2.25
     說
    2.23
     uitgenodigd
    2.17
    鴣
    2.16
    Depending
    2.13
    immen
    2.13
     quando
    2.11
    Activations Density 0.001%

    No Known Activations