© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259318
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.60
    0
    0.54
    5
    0.54
    les
    0.54
    car
    0.54
    fragt
    0.53
    rey
    0.52
    e
    0.52
    <strong>
    0.52
    ha
    0.52
    POSITIVE LOGITS
     توسیع
    0.60
    ચે
    0.54
    ڈیو
    0.52
    કરણ
    0.50
    چم
    0.49
    ειο
    0.49
    ریٹر
    0.48
    ریک
    0.47
    ચી
    0.47
    ቝ
    0.47
    Activations Density 0.004%

    No Known Activations