© 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. 14562
    Prev
    Next
    INDEX
    Explanations

    Wrapper

    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
    ſſen
    -2.86
    s
    -2.47
    菒
    -2.25
    AddTagHelper
    -2.14
     mayoría
    -2.06
     stehenden
    -2.05
     завое
    -2.03
     intelligente
    -2.03
    鴒
    -2.03
     vnnd
    -1.99
    POSITIVE LOGITS
    л
    2.52
     aktuellen
    2.50
    aimana
    2.48
     Furthermore
    2.38
    先は
    2.28
    These
    2.28
    !”
    2.27
     welchem
    2.23
    灕
    2.22
    ).
    2.20
    Activations Density 0.006%

    No Known Activations