© 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. 170149
    Prev
    Next
    INDEX
    Explanations

    housewarming, our door, golf sponsor

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

    words with multiple meanings

    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
     equivari
    0.45
    ﾝ
    0.44
     estet
    0.43
     Aesthetic
    0.43
     dollari
    0.42
     ডলার
    0.41
     Dollars
    0.41
     Preferred
    0.41
     Sylvester
    0.41
    െടു
    0.41
    POSITIVE LOGITS
    ے
    0.61
    ү
    0.55
    ि
    0.52
     প্রতিনি
    0.52
     lebens
    0.51
    िरा
    0.50
    िल्
    0.50
    ියා
    0.49
     〢
    0.48
    يرة
    0.47
    Activations Density 0.000%

    No Known Activations