© 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. 44806
    Prev
    Next
    INDEX
    Explanations

    transportation and traffic matters

    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
    стит
    -1.20
    יך
    -1.18
    astră
    -1.17
    ње
    -1.17
     român
    -1.15
    illite
    -1.15
    shadowOpacity
    -1.14
     gitara
    -1.14
    gridad
    -1.12
    西兰
    -1.12
    POSITIVE LOGITS
     is
    1.32
     намного
    1.21
    ├
    1.11
     »
    1.05
    Æ
    1.05
    cannot
    1.04
    ing
    1.02
    /
    1.01
    Do
    1.00
    must
    1.00
    Activations Density 0.080%

    No Known Activations