© 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. 44685
    Prev
    Next
    INDEX
    Explanations

    awards and honours

    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
    躥
    -1.47
    
    -1.47
    
    -1.41
    呟
    -1.40
    臜
    -1.39
    ſſen
    -1.36
     nieuwe
    -1.34
     célè
    -1.34
     zilver
    -1.34
    ってしまった
    -1.33
    POSITIVE LOGITS
     after
    1.76
     from
    1.71
     by
    1.62
     on
    1.61
     for
    1.52
     through
    1.51
     of
    1.48
    sistors
    1.47
     had
    1.45
     since
    1.40
    Activations Density 0.014%

    No Known Activations