© 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. 69137
    Prev
    Next
    INDEX
    Explanations

    English and foreign language words

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

    traveler, stranger, holidays

    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
    ote
    0.47
    dte
    0.47
    હેરા
    0.46
    ෝ
    0.46
     dormancy
    0.45
    重大
    0.45
    тт
    0.45
    ката
    0.45
    回収
    0.44
    દ્ધ
    0.44
    POSITIVE LOGITS
     cities
    0.49
     साथी
    0.48
     բ
    0.48
     Mighty
    0.46
     taver
    0.46
     নিজের
    0.44
    Ј
    0.44
    पू
    0.43
     χώ
    0.43
    sels
    0.43
    Activations Density 0.001%

    No Known Activations