© 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. 28806
    Prev
    Next
    INDEX
    Explanations

    modern house reviews

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

    end turn

    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
    t
    0.45
     पति
    0.44
    ulph
    0.43
    atán
    0.43
    g
    0.43
    methyl
    0.42
    max
    0.41
    ographs
    0.41
    ockeys
    0.41
    ak
    0.40
    POSITIVE LOGITS
     pek
    0.56
     sembra
    0.55
     arasında
    0.54
    نما
    0.54
     quotidienne
    0.52
     Kraków
    0.51
    hattim
    0.51
    뎐
    0.50
     rampage
    0.50
    間
    0.50
    Activations Density 0.000%

    No Known Activations