© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    conversational turns

    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
     resumo
    1.41
     resumen
    1.28
     szüks
    1.28
     ١
    1.27
     первая
    1.21
     desiderio
    1.17
     první
    1.17
     birkaç
    1.16
     ersten
    1.16
     velik
    1.15
    POSITIVE LOGITS
    cm
    0.93
    ylmethyl
    0.91
    kg
    0.85
     trips
    0.85
     litres
    0.84
    kcal
    0.84
    km
    0.82
     holes
    0.81
    円
    0.81
    mph
    0.79
    Activations Density 0.905%

    No Known Activations