© 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. 240648
    Prev
    Next
    INDEX
    Explanations

    countries. engagement team movie sequence. city

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     sá
    0.59
     té
    0.56
    罾
    0.56
     entrar
    0.55
     discipl
    0.53
     ú
    0.52
     Հ
    0.52
     ת
    0.52
     ፣
    0.50
     descubrir
    0.50
    POSITIVE LOGITS
    taxes
    0.64
    faux
    0.56
    milk
    0.56
    involved
    0.52
    carriers
    0.50
    altered
    0.49
    rau
    0.49
    rounds
    0.49
    airflow
    0.49
    revenue
    0.48
    Activations Density 0.000%

    No Known Activations