© 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. 14838
    Prev
    Next
    INDEX
    Explanations

    no mistake, no time, no illusions, no secret

    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
    --"
    -1.59
     mantenere
    -1.51
    prove
    -1.48
    変わらず
    -1.46
     díky
    -1.45
     ridurre
    -1.45
    ER
    -1.44
     núcleos
    -1.44
     troviamo
    -1.43
     mogą
    -1.41
    POSITIVE LOGITS
     istor
    1.32
     даже
    1.29
    所謂
    1.28
    zęd
    1.27
     berbahaya
    1.27
     mengubah
    1.25
     otra
    1.23
    сколько
    1.22
     relation
    1.22
    》.
    1.21
    Activations Density 0.012%

    No Known Activations