© 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. 13738
    Prev
    Next
    INDEX
    Explanations

    virtual assistant

    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
    ের
    3.84
    u
    3.58
    ו
    3.33
    uie
    3.12
    ع
    3.10
    десят
    2.90
    いった
    2.90
    ோ
    2.86
    dür
    2.77
    लिये
    2.75
    POSITIVE LOGITS
    ಾಯಕ
    2.82
    িয়োগ
    2.62
    یز
    2.48
    falling
    2.40
    ólicos
    2.36
     colloidal
    2.26
     cryogenic
    2.24
     observations
    2.17
    igts
    2.17
     ఉంట
    2.16
    Activations Density 0.022%

    No Known Activations