© 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. 84581
    Prev
    Next
    INDEX
    Explanations

    Following is

    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
     of
    -1.75
     that
    -1.60
     to
    -1.49
     for
    -1.47
     =
    -1.44
     between
    -1.41
     people
    -1.38
     special
    -1.38
     speziell
    -1.38
     only
    -1.34
    POSITIVE LOGITS
     inond
    1.50
    Autres
    1.45
     pérd
    1.43
     ancha
    1.38
     esquerda
    1.37
    цыі
    1.35
    薷
    1.34
     ouest
    1.31
     cadeira
    1.30
    嗐
    1.30
    Activations Density 0.163%

    No Known Activations