© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34200
    Prev
    Next
    INDEX
    Explanations

    approach type Ex

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

    numbers, including numerals and numeric measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -1.66
    ;
    -1.52
     S
    -1.42
     The
    -1.30
     it
    -1.24
     E
    -1.23
     T
    -1.23
     Viitattu
    -1.23
    it
    -1.22
     M
    -1.21
    POSITIVE LOGITS
    </h2>
    2.63
    </strong>
    2.16
    </b>
    1.90
    </em>
    1.70
    </h3>
    1.65
    もあって
    1.57
    ,</
    1.53
    ")]
    1.52
    ':
    
    1.50
    </h4>
    1.48
    Activations Density 0.008%

    No Known Activations