© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66193
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     lahat
    -1.00
    matite
    -0.98
    whether
    -0.93
     menganggap
    -0.92
    Whether
    -0.89
     belki
    -0.89
     berangkat
    -0.85
     levante
    -0.85
     penyakit
    -0.85
     here
    -0.85
    POSITIVE LOGITS
     rồi
    0.96
    expiresIn
    0.88
     entonces
    0.88
     gấp
    0.85
     still
    0.84
     todavía
    0.83
    ն
    0.82
    行き
    0.81
     ještě
    0.80
     ancora
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.