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. 2877
    Prev
    Next
    INDEX
    Explanations

    use of things

    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
    ニング
    1.21
    過去
    1.19
    当前
    1.13
    ijken
    1.13
    以下
    1.09
    或
    1.04
     ज्वालामुखी
    1.02
    切换
    1.01
    或者是
    1.01
    もしくは
    1.00
    POSITIVE LOGITS
     surgiu
    1.01
     levou
    0.96
     lij
    0.96
     krav
    0.95
     souci
    0.93
     these
    0.90
     Hem
    0.90
     పాల్గొన్నారు
    0.88
     ä
    0.87
     stable
    0.87
    Activations Density 0.449%

    No Known Activations