© 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. 42541
    Prev
    Next
    INDEX
    Explanations

    private spaces

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

    local domestic household

    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
    水源
    0.29
    yrs
    0.29
    蕃
    0.28
    政治
    0.28
    ällä
    0.28
    ニ
    0.28
    🗾
    0.28
    מש
    0.28
    世界
    0.27
    chloride
    0.27
    POSITIVE LOGITS
     Rookie
    0.31
     privé
    0.31
     playroom
    0.31
     personale
    0.30
     WPF
    0.30
     Wooden
    0.30
     Nursery
    0.30
     privata
    0.30
     private
    0.30
     privately
    0.30
    Activations Density 0.194%

    No Known Activations