© 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. 225035
    Prev
    Next
    INDEX
    Explanations

    astrological speculative foreign

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

    Crick, species, information flow

    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
     قو
    0.45
    áty
    0.44
    ো
    0.43
    AQP
    0.43
     Lobkovic
    0.42
    ა
    0.42
     المركز
    0.41
     مرکز
    0.41
    typ
    0.39
     وە
    0.39
    POSITIVE LOGITS
    钿
    0.50
     astrolog
    0.48
     scheming
    0.47
     astrological
    0.45
    标记
    0.45
    という意味
    0.43
     speculative
    0.43
     далеко
    0.43
     anlamına
    0.43
    气
    0.43
    Activations Density 0.001%

    No Known Activations