© 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. 76583
    Prev
    Next
    INDEX
    Explanations

    places and concepts

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

    practical difficulties, lack protective, need capacity

    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
    oor
    0.48
    yana
    0.47
    胿
    0.46
     برابر
    0.46
    pana
    0.46
     solidar
    0.46
     Editable
    0.46
     పెరుగు
    0.46
     Fonts
    0.45
     Hazrat
    0.45
    POSITIVE LOGITS
    @[+][
    0.49
    йно
    0.47
    ุม
    0.47
    )"
    0.46
    าด
    0.44
     vac
    0.43
    อังกฤษ
    0.43
    生ま
    0.42
    🏟
    0.42
    ๗
    0.41
    Activations Density 0.003%

    No Known Activations