© 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. 109169
    Prev
    Next
    INDEX
    Explanations

    drives, cherished, kill

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

    words following "how"

    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
     fair
    0.51
    du
    0.50
    mare
    0.48
     storytelling
    0.47
     //
    0.45
     recomand
    0.44
     referee
    0.44
     was
    0.44
    was
    0.43
     penting
    0.43
    POSITIVE LOGITS
    쮿
    0.50
     امریکا
    0.46
     Hadamard
    0.46
    یک
    0.46
    کس
    0.45
    ومن
    0.45
    کو
    0.44
     آمریکا
    0.44
    स
    0.44
    ників
    0.44
    Activations Density 0.000%

    No Known Activations