Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2860
    Prev
    Next
    INDEX
    Explanations

    current snippet

    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
     থাকত
    1.07
    üns
    1.05
     रहता
    1.05
     देता
    1.04
     unterschied
    1.03
    ⍵
    1.02
     Während
    1.01
    िकाओं
    1.00
     hilft
    1.00
    するとき
    0.99
    POSITIVE LOGITS
     already
    1.75
    都已经
    1.69
    已经
    1.65
     sudah
    1.63
    就已经
    1.60
    既に
    1.59
    すでに
    1.58
    已经被
    1.55
    已经在
    1.54
    Already
    1.52
    Activations Density 1.025%

    No Known Activations