© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74676
    Prev
    Next
    INDEX
    Explanations

    evaluation by standards or logic

    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
     for
    -2.09
     on
    -1.80
     without
    -1.70
     from
    -1.65
     using
    -1.64
     all
    -1.63
     in
    -1.63
     with
    -1.60
     about
    -1.55
     superbly
    -1.51
    POSITIVE LOGITS
    "]();
    1.61
    Could
    1.51
    offers
    1.50
    ところは
    1.47
    those
    1.45
     interrom
    1.42
     детей
    1.41
     unending
    1.41
     engend
    1.41
     ARISING
    1.41
    Activations Density 0.015%

    No Known Activations