© 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. 262
    Prev
    Next
    INDEX
    Explanations

    Fill in the blank or drawing prompts

    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
     struggling
    1.08
     shaped
    1.06
    obbly
    1.02
     heavily
    1.00
     bunch
    0.99
    angled
    0.99
     strongly
    0.96
     ‘
    0.95
     supposedly
    0.95
     weapons
    0.94
    POSITIVE LOGITS
     descrição
    2.45
     descrizione
    2.40
     organizações
    2.39
     informações
    2.30
     descripción
    2.29
     análise
    2.24
     instituições
    2.24
     valutazione
    2.23
     organizaciones
    2.21
     avaliação
    2.19
    Activations Density 0.260%

    No Known Activations