© 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. 142266
    Prev
    Next
    INDEX
    Explanations

    negotiations, search, dates, contacts

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

    specific character role

    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
    ექს
    0.45
    飯店
    0.44
     empate
    0.44
    RECT
    0.42
     テーブル
    0.42
    }^{*}-
    0.42
    "="
    0.42
    رة
    0.42
    BibitemShut
    0.41
    punten
    0.41
    POSITIVE LOGITS
    ด
    0.45
     Britain
    0.44
     Virg
    0.43
    ുക
    0.43
     Johnson
    0.43
     Terry
    0.43
     Benn
    0.42
     Macon
    0.42
     জায়গা
    0.41
     daz
    0.40
    Activations Density 0.002%

    No Known Activations