© 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-65K
    7. 64048
    Prev
    Next
    INDEX
    Explanations

    lists, punctuation, and context

    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_65k_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
    (
    0.48
    《
    0.44
    у
    0.43
     bát
    0.42
    بط
    0.42
     fabricant
    0.41
    ()
    0.40
    Night
    0.40
     $
    0.40
    Portugal
    0.39
    POSITIVE LOGITS
    posY
    0.45
     кеңселер
    0.42
     आपस
    0.42
    indari
    0.42
    unsplash
    0.42
    kolah
    0.41
     टीच
    0.40
    emap
    0.40
    ographed
    0.40
     হইয়৷
    0.40
    Activations Density 0.002%

    No Known Activations