© 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. 127790
    Prev
    Next
    INDEX
    Explanations

    you know

    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
     each
    -1.44
     decidieron
    -1.39
    身为
    -1.34
     verschiedener
    -1.31
     erau
    -1.29
     外観
    -1.25
     سایر
    -1.24
    ၜ
    -1.24
    Postcode
    -1.22
     trekken
    -1.22
    POSITIVE LOGITS
     –
    1.64
     where
    1.32
    EdgeInsets
    1.23
     #
    1.17
    on
    1.16
    a
    1.16
     —
    1.13
    ンテナ
    1.13
     It
    1.12
     -=
    1.11
    Activations Density 0.049%

    No Known Activations