© 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. 56061
    Prev
    Next
    INDEX
    Explanations

    comfortable observing

    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
     ಕಬ್ಬಿಣ
    0.55
     ಅಥವಾ
    0.53
    NOMBRE
    0.49
     ଯ
    0.48
    Tienes
    0.48
     മത
    0.48
     yoki
    0.47
    cesz
    0.47
    名稱
    0.47
     அல்லது
    0.47
    POSITIVE LOGITS
    0.69
     <
    0.59
     Spotify
    0.55
     (
    0.54
     scoping
    0.54
    ,
    0.52
    \
    0.50
     >
    0.50
     k
    0.50
     LinkedIn
    0.50
    Activations Density 0.011%

    No Known Activations