© 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. 241073
    Prev
    Next
    INDEX
    Explanations

    Household use, extension, collaborator

    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
    SYMBOL
    0.52
    перыі
    0.47
    ўся
    0.47
    ()}\
    0.47
    ǎ
    0.47
    があ
    0.46
    كتوبر
    0.46
     때문에
    0.46
    يئة
    0.45
    利
    0.45
    POSITIVE LOGITS
     collaborate
    0.43
     ক্রি
    0.43
     collaborative
    0.42
     Household
    0.42
     lego
    0.42
     साजिश
    0.42
     Locker
    0.41
     Smart
    0.41
     loved
    0.41
     Breakfast
    0.40
    Activations Density 0.001%

    No Known Activations