© 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. 73285
    Prev
    Next
    INDEX
    Explanations

    infrastructure and systems

    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
    Because
    -1.52
     OGSÅ
    -1.47
    Since
    -1.42
     îles
    -1.42
     ausdrück
    -1.41
    When
    -1.39
     publiek
    -1.39
    Nearly
    -1.35
    뒀
    -1.34
    ığımız
    -1.33
    POSITIVE LOGITS
     a
    1.49
    ”)
    1.47
     infrastructure
    1.45
    orer
    1.40
     plana
    1.36
     fortal
    1.32
    淳
    1.30
     observa
    1.30
     sistem
    1.30
    }$
    1.30
    Activations Density 0.081%

    No Known Activations