© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1413
    Prev
    Next
    INDEX
    Explanations

    learning languages

    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_16k_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
     lowest
    0.51
     naive
    0.51
     N
    0.50
     initial
    0.50
     Bereits
    0.46
     L
    0.45
     final
    0.45
     M
    0.44
     SLC
    0.43
     abbreviation
    0.43
    POSITIVE LOGITS
    ехать
    0.48
     nešto
    0.47
    ла
    0.46
    дьми
    0.46
     chứ
    0.44
     tồn
    0.44
    ोनेशिया
    0.43
     coś
    0.43
     існу
    0.43
     അങ്ങനെ
    0.43
    Activations Density 0.457%

    No Known Activations