© 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. 17-GEMMASCOPE-2-RES-16K
    7. 871
    Prev
    Next
    INDEX
    Explanations

    Supabase create code

    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_17_width_16k_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
    ській
    1.23
    lijk
    1.19
    
    1.19
    ському
    1.17
    任何
    1.15
    ською
    1.12
    ским
    1.12
    忓
    1.11
    ським
    1.08
    佹
    1.08
    POSITIVE LOGITS
     dozen
    1.33
     wenige
    1.33
     wenigen
    1.28
     hundred
    1.28
    thousand
    1.22
     clarifications
    1.20
     thousand
    1.19
     wiggle
    1.17
    许
    1.16
     extra
    1.15
    Activations Density 0.610%

    No Known Activations