© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 301
    Prev
    Next
    INDEX
    Explanations

    years 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_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
    h
    0.76
    ns
    0.74
    ndes
    0.73
    νου
    0.73
    as
    0.70
    9
    0.69
         
    0.69
    ილი
    0.68
    нами
    0.66
       
    0.66
    POSITIVE LOGITS
     tomado
    0.97
     piezas
    0.93
     notícias
    0.82
     médio
    0.81
     parlato
    0.81
     gestión
    0.81
     absolutamente
    0.81
     tenido
    0.80
     llevado
    0.80
     relacionamento
    0.79
    Activations Density 0.724%

    No Known Activations