© 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. 77628
    Prev
    Next
    INDEX
    Explanations

    stock images

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

    listing items or concepts

    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
    им
    0.50
    ுமி
    0.49
    वेलकम
    0.48
    ու
    0.47
    brush
    0.47
    ву
    0.46
    ᱗
    0.46
    Khi
    0.46
    cuando
    0.45
    बा
    0.45
    POSITIVE LOGITS
     concurrence
    0.54
     детали
    0.52
    ölker
    0.51
     köl
    0.51
     Fighting
    0.49
     戦
    0.49
     무엇
    0.49
     पहाड़ों
    0.48
     壁
    0.47
     Stiftung
    0.47
    Activations Density 0.000%

    No Known Activations