© 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. 15094
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and identity terms

    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
     cuando
    -3.11
    })
    -2.61
    ="
    -2.53
    秾
    -2.53
    }:
    -2.33
    ):
    -2.31
    亹
    -2.28
    ":
    -2.22
    },
    -2.22
    說道
    -2.19
    POSITIVE LOGITS
    ↵
    2.95
     for
    2.23
    淠
    2.09
     ponú
    1.97
    屺
    1.95
     as
    1.95
     Buscar
    1.91
    nipeg
    1.89
    erai
    1.88
    lingo
    1.86
    Activations Density 0.002%

    No Known Activations