© 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. 125949
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
    ធ្វ
    0.28
     éviter
    0.27
     accountants
    0.27
    Н
    0.26
     savent
    0.26
     Verlust
    0.26
    АСС
    0.26
     constate
    0.25
     tempus
    0.25
     আসবেন
    0.25
    POSITIVE LOGITS
    in
    0.26
    (
    0.24
    -
    0.24
    יי
    0.24
    ὺ
    0.23
    ו
    0.22
    ina
    0.22
    il
    0.22
    Poppins
    0.22
    বের
    0.22
    Activations Density 0.024%

    No Known Activations