© 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. 52460
    Prev
    Next
    INDEX
    Explanations

    namespace std

    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
    ter
    0.57
    t
    0.57
    z
    0.54
    y
    0.53
    az
    0.52
    ta
    0.52
    ti
    0.51
    Ann
    0.51
    a
    0.49
    ine
    0.48
    POSITIVE LOGITS
    
    0.55
     alloys
    0.54
     aerodynamics
    0.53
     résult
    0.52
     peuple
    0.52
     ruchu
    0.49
     calcio
    0.48
     eukaryotes
    0.48
     électriques
    0.48
     stos
    0.47
    Activations Density 0.010%

    No Known Activations