© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8801
    Prev
    Next
    INDEX
    Explanations

    states with

    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
    Ekster
    -1.52
     surn
    -1.45
    ÕES
    -1.39
    )+\
    -1.37
    дры
    -1.34
    鐽
    -1.31
     considérons
    -1.31
     singuli
    -1.30
     لأنه
    -1.30
    ཥ
    -1.27
    POSITIVE LOGITS
     with
    1.70
     where
    1.66
     like
    1.62
     such
    1.58
    in
    1.57
     and
    1.55
     setAddress
    1.53
    ar
    1.43
     or
    1.43
     through
    1.42
    Activations Density 0.023%

    No Known Activations