© 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. 222369
    Prev
    Next
    INDEX
    Explanations

    before p/maybe/their/Chou/sitting/to/With/police

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

    multilingual snippets

    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
    \
    0.68
     labels
    0.51
     envelopes
    0.51
    '
    0.50
     sulfonic
    0.49
    OBI
    0.48
     tarifa
    0.48
     submissions
    0.48
     hydrogens
    0.47
     raids
    0.47
    POSITIVE LOGITS
     سین
    0.50
     Choibalsan
    0.44
     यही
    0.44
     তথ
    0.44
    syntax
    0.43
     δι
    0.43
    찾
    0.42
     яв
    0.42
    สัน
    0.41
    dipl
    0.41
    Activations Density 0.000%

    No Known Activations