© 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. 130636
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     etkili
    -1.05
    These
    -1.02
    recette
    -0.94
    schwar
    -0.93
    Several
    -0.92
     gillar
    -0.91
    dacia
    -0.90
    reducer
    -0.89
    alipay
    -0.89
    二十
    -0.88
    POSITIVE LOGITS
    avra
    1.02
    ﻳ
    0.99
     GERMAN
    0.99
    conce
    0.98
    omitempty
    0.98
    lgari
    0.96
    xer
    0.96
    vres
    0.94
    ctez
    0.94
    ってしまった
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.