© 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. 27208
    Prev
    Next
    INDEX
    Explanations

    yoga, stimulate, maintains, Net

    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
     예를
    0.44
    用に
    0.44
     باستخدام
    0.43
    殓
    0.42
     অসুবিধা
    0.42
     গিয়ে
    0.42
     앞에
    0.41
     suitable
    0.41
     جوړونکو
    0.41
     dynamical
    0.41
    POSITIVE LOGITS
    9
    0.48
    2
    0.43
    L
    0.42
     års
    0.41
    C
    0.41
    s
    0.39
     bikes
    0.39
    ulz
    0.38
    إ
    0.38
    us
    0.38
    Activations Density 0.004%

    No Known Activations