© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 116
    Prev
    Next
    INDEX
    Explanations

    objects and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.90
    혀
    0.90
    tte
    0.86
     правом
    0.84
    さすが
    0.84
     prava
    0.84
    ときの
    0.83
    之为
    0.83
     زمانے
    0.82
    갓
    0.82
    POSITIVE LOGITS
    ḵ
    1.07
    agricult
    1.03
    ág
    1.02
    os
    1.01
    ĩa
    1.01
    ifferentiated
    0.98
    rones
    0.97
     Livermore
    0.95
    awcy
    0.94
    opee
    0.93
    Activations Density 0.000%

    No Known Activations