© 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. 22356
    Prev
    Next
    INDEX
    Explanations

    attempting or venturing

    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
     blancas
    -1.65
    \
    -1.62
     vermelhas
    -1.62
    AndSet
    -1.59
     tranquila
    -1.53
    線を
    -1.43
     그리고
    -1.43
    
    -1.39
     encantado
    -1.39
     Septembre
    -1.38
    POSITIVE LOGITS
     same
    1.59
     compleanno
    1.58
    </b>
    1.57
    y
    1.55
    tômes
    1.48
    codiles
    1.45
    éclairage
    1.43
    automne
    1.41
     vorhandenen
    1.40
     quantità
    1.36
    Activations Density 0.031%

    No Known Activations