© 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. 58924
    Prev
    Next
    INDEX
    Explanations

    Act/Scene descriptors

    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
    tbx
    -1.90
     informaron
    -1.77
    ^(@
    -1.68
    驸
    -1.64
    っていました
    -1.64
     ſtre
    -1.64
    produkter
    -1.63
     publications
    -1.59
    jątk
    -1.57
     who
    -1.55
    POSITIVE LOGITS
     an
    1.49
     or
    1.49
     the
    1.39
    Sejarah
    1.38
    所有
    1.36
     all
    1.28
    Though
    1.28
    なので
    1.27
    After
    1.26
     epitom
    1.26
    Activations Density 0.063%

    No Known Activations