© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123922
    Prev
    Next
    INDEX
    Explanations

    release of things

    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
    at
    -2.22
    }
    -2.20
     what
    -2.14
    you
    -2.11
     through
    -2.00
     for
    -2.00
    what
    -1.95
    </h1>
    -1.92
     if
    -1.91
    It
    -1.91
    POSITIVE LOGITS
     jejich
    2.09
    咘
    1.97
    掼
    1.96
    𖣔
    1.96
    蟳
    1.95
    ḿ
    1.93
    lulu
    1.91
    ꙰
    1.88
    尪
    1.87
     patienter
    1.86
    Activations Density 0.034%

    No Known Activations