© 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-65K
    7. 47081
    Prev
    Next
    INDEX
    Explanations

    Key followed by categories

    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
     Cádiz
    0.53
    ড়ান্ত
    0.46
    banam
    0.45
     Itália
    0.44
     Балт
    0.43
    ַ
    0.43
     vadanti
    0.42
     Espanha
    0.42
    élev
    0.41
    ","$
    0.41
    POSITIVE LOGITS
     bisher
    0.46
     nasty
    0.46
     tinkering
    0.46
     flog
    0.46
     coal
    0.45
     الر
    0.45
     kup
    0.45
     rant
    0.43
     eight
    0.43
     fireworks
    0.42
    Activations Density 0.009%

    No Known Activations