© 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. 34-GEMMASCOPE-RES-131K
    7. 30359
    Prev
    Next
    INDEX
    Explanations

    words followed by specific details

    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_34/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
     logements
    -1.27
    ländischen
    -1.20
    maß
    -1.18
    ñar
    -1.16
    цепт
    -1.15
    barer
    -1.12
    vertre
    -1.11
    baly
    -1.09
     Bartol
    -1.09
     séjours
    -1.09
    POSITIVE LOGITS
     focusing
    1.54
     during
    1.45
     very
    1.39
     at
    1.38
     or
    1.34
     quite
    1.34
     focused
    1.30
     doing
    1.29
     supposedly
    1.25
     by
    1.24
    Activations Density 0.018%

    No Known Activations