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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1061
    Prev
    Next
    INDEX
    Explanations

    function return values and operands

    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_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
    <0xC2>
    1.07
      
    1.06
     DIY
    1.00
    <start_of_image>
    0.99
     CRO
    0.88
    aque
    0.86
    acup
    0.82
     shakes
    0.82
     Drak
    0.81
     Browns
    0.81
    POSITIVE LOGITS
     _$_
    1.52
    hFile
    1.41
    సో
    1.40
    зидента
    1.35
    ソファ
    1.32
     milliseconds
    1.31
     함수의
    1.31
     hostname
    1.27
     instantiated
    1.27
     firstName
    1.27
    Activations Density 0.238%

    No Known Activations