© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111413
    Prev
    Next
    INDEX
    Explanations

    OpenZWave, Days of Our Lives, processing, ASF, Client, OBTComparable

    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
     乗
    -1.23
    er
    -1.23
    os
    -1.20
     them
    -1.17
    us
    -1.15
     Nt
    -1.15
    ца
    -1.14
    ISCHE
    -1.14
     wt
    -1.13
     fossero
    -1.13
    POSITIVE LOGITS
    φορά
    1.44
    <th>
    1.42
    rétaire
    1.39
    訫
    1.39
     As
    1.37
    	
    1.36
     hasta
    1.34
    tività
    1.34
    handleError
    1.34
    )}{
    1.33
    Activations Density 0.005%

    No Known Activations