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. 2910
    Prev
    Next
    INDEX
    Explanations

    asking to rate or state preference

    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
     Gives
    1.11
     "(
    1.06
     Alerts
    1.06
    𝙣
    1.04
     Yên
    1.02
     документи
    1.02
     Statements
    1.02
     ":
    1.01
     telev
    1.01
     '
    1.01
    POSITIVE LOGITS
    three
    1.48
    三种
    1.35
    rim
    1.30
     इत्यादि
    1.27
    など
    1.27
     tiga
    1.27
    etc
    1.26
     وغیرہ
    1.26
    linear
    1.26
    texture
    1.26
    Activations Density 0.001%

    No Known Activations