© 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. 66690
    Prev
    Next
    INDEX
    Explanations

    operating systems and devices

    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
     it
    -1.59
     because
    -1.55
     they
    -1.45
     did
    -1.45
     which
    -1.45
    一千
    -1.45
     certainly
    -1.43
     each
    -1.40
     had
    -1.34
    他也
    -1.28
    POSITIVE LOGITS
     других
    1.52
    Including
    1.45
    ➆
    1.33
    choix
    1.31
     específicos
    1.31
     tuss
    1.30
     pained
    1.29
    MANY
    1.27
     of
    1.26
    Tanto
    1.25
    Activations Density 0.080%

    No Known Activations