© 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. 15270
    Prev
    Next
    INDEX
    Explanations

    software dependencies

    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
    ."
    -1.89
    ":
    -1.78
    or
    -1.77
    –
    -1.63
    of
    -1.59
    ,”
    -1.56
    </h5>
    -1.49
     if
    -1.48
    ский
    -1.48
     “
    -1.47
    POSITIVE LOGITS
    président
    1.80
    𝟭
    1.70
     破解
    1.70
    
    1.66
     грудня
    1.61
    Verses
    1.60
     kuhusu
    1.59
     éves
    1.58
     정보
    1.57
    纐
    1.55
    Activations Density 0.052%

    No Known Activations