© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 204286
    Prev
    Next
    INDEX
    Explanations

    information about homeowners

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

    becausecrucialinformationHoweverresonate

    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
     POINTS
    0.48
    WAR
    0.47
    nano
    0.46
     WAR
    0.46
     राइड
    0.46
     カバー
    0.46
     nanoparticle
    0.46
     ;
    0.46
    MUST
    0.46
     jednu
    0.45
    POSITIVE LOGITS
     erinn
    0.46
    uie
    0.43
    zość
    0.43
    攪
    0.40
    फ्त
    0.39
     deem
    0.38
     nás
    0.37
    behör
    0.37
    ى
    0.37
    Bien
    0.37
    Activations Density 0.001%

    No Known Activations