© 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. 102476
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions

    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
     таких
    -1.79
     revamped
    -1.48
    selbe
    -1.48
    wahati
    -1.48
     sottile
    -1.45
     chiara
    -1.44
    𖥧
    -1.44
     のみ
    -1.44
     doppia
    -1.43
     específica
    -1.42
    POSITIVE LOGITS
     for
    1.45
     haar
    1.43
     even
    1.42
    )
    1.40
     by
    1.40
    amientos
    1.31
    šne
    1.30
    鯪
    1.30
    eksi
    1.26
    lichkeit
    1.25
    Activations Density 0.012%

    No Known Activations