© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 378
    Prev
    Next
    INDEX
    Explanations

    Spanish, French, and Portuguese articles

    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
     the
    1.98
    with
    1.70
    2
    1.68
    ally
    1.66
    the
    1.66
     and
    1.64
     with
    1.64
    1
    1.63
    4
    1.61
    and
    1.57
    POSITIVE LOGITS
     dispositivo
    2.83
     ámbito
    2.76
     edifício
    2.72
     órgão
    2.70
     terzo
    2.70
     prédio
    2.66
     funcionamento
    2.65
     modèle
    2.63
     modello
    2.62
     cambiamento
    2.61
    Activations Density 0.116%

    No Known Activations