© 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. 7-GEMMASCOPE-2-RES-16K
    4. 1241
    Prev
    Next
    INDEX
    Explanations

    how questions

    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_7_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
     up
    1.87
    l
    1.81
    up
    1.75
    hose
    1.60
     let
    1.56
    pun
    1.55
     Gresham
    1.53
     Up
    1.52
    w
    1.50
    ս
    1.47
    POSITIVE LOGITS
     diferenças
    2.69
    éristiques
    2.58
     importância
    2.47
     différences
    2.46
     Inhalt
    2.45
     prédio
    2.42
     disponibilités
    2.40
    Cómo
    2.34
     cómo
    2.32
     dní
    2.31
    Activations Density 0.597%

    No Known Activations