© 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. 42866
    Prev
    Next
    INDEX
    Explanations

    type of

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

    hydraulic pump

    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
    ла
    0.50
    át
    0.47
    ш
    0.46
    ạo
    0.46
    site
    0.46
    ê
    0.46
    ú
    0.46
    я
    0.45
    ên
    0.45
    read
    0.44
    POSITIVE LOGITS
     lubric
    0.56
     previewBuilder
    0.53
     presse
    0.53
     alkalies
    0.53
     towing
    0.52
     uključ
    0.52
     জড়িত
    0.52
     incluido
    0.51
     stoi
    0.51
     îmb
    0.50
    Activations Density 0.000%

    No Known Activations