© 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. 47877
    Prev
    Next
    INDEX
    Explanations

    statements, objects, locations

    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
    溱
    0.52
    نا
    0.50
    য়েছে
    0.49
    deployRoot
    0.48
    자로
    0.48
    Brow
    0.47
     authorise
    0.46
    Demi
    0.46
    Renew
    0.46
    েম্বরে
    0.46
    POSITIVE LOGITS
     (
    0.58
     indicating
    0.51
     (\
    0.50
    \},
    0.50
     spectroscopic
    0.49
     Coupling
    0.48
     $\
    0.48
     elucid
    0.47
     silico
    0.47
     collinear
    0.47
    Activations Density 0.036%

    No Known Activations