© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    melancholic and dark themes

    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
    fresh
    1.13
     Fresh
    1.12
    Fresh
    1.06
     отсутствует
    0.95
    igham
    0.93
    omit
    0.93
     fresh
    0.90
     イ
    0.89
     <
    0.88
    予め
    0.88
    POSITIVE LOGITS
     crescendo
    1.58
     increasingly
    1.54
     बढ़कर
    1.46
     becoming
    1.44
     progressively
    1.39
     culminating
    1.39
     progressivement
    1.35
    越来越
    1.34
     Increasingly
    1.30
     eventually
    1.29
    Activations Density 1.960%

    No Known Activations