© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77780
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and variables

    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_34/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
    ージー
    -0.78
    日向
    -0.75
    REQUEST
    -0.75
    鈴木
    -0.73
    factorial
    -0.73
     یاد
    -0.72
     festivities
    -0.72
     Still
    -0.72
    VERTIS
    -0.70
     entweder
    -0.70
    POSITIVE LOGITS
    }=-
    3.53
    }=-\
    3.31
    =-
    3.30
    )=-
    3.03
    )=-\
    2.88
    =-\
    2.84
    ]=-
    2.73
    =−
    2.63
     =-\
    2.59
     $=-
    2.30
    Activations Density 0.058%

    No Known Activations