© 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. 55951
    Prev
    Next
    INDEX
    Explanations

    locating specific places and services

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

    key concepts completion

    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
     වැ
    0.47
    女士
    0.47
    🌩
    0.45
     caracteres
    0.45
     الخمسه
    0.44
     kama
    0.43
    य
    0.43
     夕
    0.43
     因
    0.42
    人に
    0.42
    POSITIVE LOGITS
    c
    0.47
     elet
    0.45
     Orleans
    0.43
    éről
    0.43
     Dumping
    0.43
    ciò
    0.42
     collectiv
    0.41
    adó
    0.41
     projecting
    0.40
    쇠
    0.40
    Activations Density 0.000%

    No Known Activations