© 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. 10878
    Prev
    Next
    INDEX
    Explanations

    examples and comparisons

    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
     (
    -1.83
     each
    -1.68
     to
    -1.63
    -1.57
     would
    -1.48
     and
    -1.44
     or
    -1.43
     involving
    -1.36
     de
    -1.30
    Each
    -1.27
    POSITIVE LOGITS
     tenemos
    1.38
    rovna
    1.38
     cazul
    1.32
    idazole
    1.31
    λαι
    1.29
    τευ
    1.28
     jednom
    1.27
    乁
    1.27
     decoraciones
    1.26
     wtedy
    1.24
    Activations Density 0.377%
    No Known Activations