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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1664
    Prev
    Next
    INDEX
    Explanations

    large quantity or range

    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
     keadaan
    1.99
     recuerdo
    1.95
    ்க்
    1.92
    RichEmbed
    1.83
    !='
    1.80
    ित्र
    1.80
     जानना
    1.80
     weap
    1.79
    เสมอ
    1.77
     যেত
    1.77
    POSITIVE LOGITS
     of
    3.53
    of
    2.87
     Of
    2.65
     của
    2.62
    Of
    2.27
     của
    2.27
    의
    2.25
     OF
    2.13
    ของ
    2.11
    的
    2.10
    Activations Density 0.934%

    No Known Activations