© 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. 179
    Prev
    Next
    INDEX
    Explanations

    contractions and descriptions

    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
     it
    1.18
     get
    1.12
     this
    1.11
    .
    1.10
     we
    1.04
     getting
    1.02
     you
    1.01
     in
    1.00
     that
    0.99
     give
    0.97
    POSITIVE LOGITS
    𒀖
    1.97
    <unused71>
    1.97
    𒀯
    1.97
    𒉪
    1.96
    𒁯
    1.94
    𒈫
    1.94
    𒌜
    1.94
    𒂆
    1.94
    𒁁
    1.94
    𒁾
    1.93
    Activations Density 7.797%

    No Known Activations