© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48345
    Prev
    Next
    INDEX
    Explanations

    first look

    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
    flakes
    -1.09
     by
    -1.09
    ſſel
    -1.05
     and
    -1.04
    Aacute
    -1.02
     thanks
    -1.02
     The
    -1.01
     ansch
    -1.00
    ikusbot
    -0.99
    ophageal
    -0.98
    POSITIVE LOGITS
     mortes
    1.27
     mariée
    1.15
    formatie
    1.15
    ?—
    1.14
    のない
    1.14
     sagt
    1.14
    łgor
    1.12
     фай
    1.09
     rempliss
    1.07
    </h2>
    1.06
    Activations Density 0.012%

    No Known Activations