© 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. 163869
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or actions

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

    opening at TB screening

    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
    ک
    0.50
     situasi
    0.49
     situaciones
    0.47
     کت
    0.47
     asociaciones
    0.47
     recomendaciones
    0.46
     pecados
    0.45
     lengkap
    0.45
    enciales
    0.44
    shares
    0.44
    POSITIVE LOGITS
    Engine
    0.48
     fermion
    0.47
    翛
    0.46
    風
    0.45
     musician
    0.45
    空気
    0.44
    净化
    0.43
     drummer
    0.43
    远程
    0.42
    /*
    0.42
    Activations Density 0.001%

    No Known Activations