© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67235
    Prev
    Next
    INDEX
    Explanations

    URL paths and requests

    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
    なども
    -1.94
     także
    -1.80
    鮠
    -1.66
     naquele
    -1.63
    我也
    -1.60
    戋
    -1.60
    も多く
    -1.59
    :"-"`
    -1.55
    ᨁ
    -1.54
     também
    -1.49
    POSITIVE LOGITS
     of
    2.19
    錞
    1.44
    ühner
    1.41
     comandante
    1.36
     sentiers
    1.35
     êtres
    1.34
    чня
    1.34
     sinnvoll
    1.30
     spirituelle
    1.30
    。
    1.28
    Activations Density 0.014%

    No Known Activations