© 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. 137627
    Prev
    Next
    INDEX
    Explanations

    Frames, monitor, recovering, Lego

    np_acts-logits-general · gemini-2.5-flash-lite

    everything that begins

    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
    и
    0.61
     โร
    0.57
    एं
    0.53
     сов
    0.50
     ڕۆ
    0.47
     כת
    0.46
    ए
    0.46
    के
    0.46
     प्रभावित
    0.46
    árez
    0.46
    POSITIVE LOGITS
    禕
    0.45
     soglas
    0.44
    rell
    0.44
    דינה
    0.43
     synopsis
    0.42
    o
    0.42
     Benutz
    0.41
    قيق
    0.41
    ycopg
    0.41
    国务
    0.41
    Activations Density 0.000%

    No Known Activations