© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26991
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    0.49
     aged
    0.46
     Pét
    0.45
     >=
    0.44
     less
    0.43
    Services
    0.43
     troubles
    0.42
     said
    0.42
     Technologie
    0.42
     faites
    0.41
    POSITIVE LOGITS
     gstlal
    0.46
    ши
    0.45
    طات
    0.45
    刹
    0.44
    كامل
    0.43
    ак
    0.42
    obat
    0.41
    wash
    0.41
     completo
    0.41
    基づ
    0.40
    Activations Density 0.001%

    No Known Activations