© 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. 1506
    Prev
    Next
    INDEX
    Explanations

    the university of

    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
     offrire
    -1.64
    ꪹ
    -1.64
    していない
    -1.63
    therosclerosis
    -1.59
    apka
    -1.53
    してない
    -1.53
     ส์
    -1.50
     rembour
    -1.47
     fourni
    -1.46
     blanches
    -1.44
    POSITIVE LOGITS
     of
    2.05
    ↵↵
    2.05
     in
    1.92
    ↵
    1.72
     as
    1.67
     but
    1.50
     what
    1.47
     and
    1.44
    </h4>
    1.38
     menengah
    1.35
    Activations Density 0.034%

    No Known Activations