© 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. 58764
    Prev
    Next
    INDEX
    Explanations

    official positions

    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
     mejores
    -1.50
     mismas
    -1.38
     compró
    -1.30
    每个人
    -1.29
     zde
    -1.27
     számára
    -1.26
     juegan
    -1.20
    每一个
    -1.20
     juega
    -1.17
     projeto
    -1.16
    POSITIVE LOGITS
     of
    1.94
     also
    1.45
     between
    1.41
     like
    1.34
     this
    1.32
     with
    1.32
     includes
    1.30
    GIUM
    1.27
     at
    1.27
    VERTIS
    1.26
    Activations Density 0.122%

    No Known Activations