© 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. 96988
    Prev
    Next
    INDEX
    Explanations

    children and team

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

    aesthetic approach

    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
    ানী
    0.49
    Dok
    0.47
    INI
    0.45
     ‬
    0.45
    Kami
    0.45
     Activ
    0.43
     Between
    0.43
     হওয়ায়
    0.43
    چه
    0.43
    ئین
    0.43
    POSITIVE LOGITS
     Morty
    0.64
     неприят
    0.49
    伐
    0.48
     dismal
    0.48
    भाषित
    0.48
    rach
    0.47
     шум
    0.47
    ີ່
    0.46
    itated
    0.46
    らす
    0.46
    Activations Density 0.000%

    No Known Activations