© 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. 85320
    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
     to
    -1.55
    canActivate
    -1.53
    vät
    -1.50
    ''');
    -1.48
     største
    -1.48
    цтва
    -1.47
    ᯅ
    -1.45
    ('.',
    -1.41
     [],
    -1.41
     one
    -1.41
    POSITIVE LOGITS
     
    2.08
     "
    1.54
     لأنه
    1.46
    彿
    1.36
    达到
    1.35
    なるべく
    1.32
     olabilir
    1.31
    6
    1.31
     afirmar
    1.30
    这让
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.