© 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. 1136
    Prev
    Next
    INDEX
    Explanations

    November and dates

    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
     devoted
    0.72
    Â
    0.71
     busy
    0.70
      
    0.67
     dedicated
    0.67
     January
    0.64
     fever
    0.64
     Sunday
    0.64
     November
    0.63
     stormy
    0.62
    POSITIVE LOGITS
    ätzung
    0.85
    ጴ
    0.83
     পারছে
    0.83
     använda
    0.82
    适配
    0.80
     পারবে
    0.79
    Resolver
    0.79
    搠
    0.79
    éndose
    0.79
    ݨ
    0.78
    Activations Density 0.142%

    No Known Activations