© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10221
    Prev
    Next
    INDEX
    Explanations

    imported as a module

    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_22_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
    <unused840>
    1.29
    <unused76>
    1.25
     calent
    1.24
     loafers
    1.23
     秋冬
    1.22
     Alhaji
    1.21
     centenary
    1.19
    castruct
    1.19
    ܛ
    1.19
     കമ
    1.18
    POSITIVE LOGITS
    two
    0.86
    序号
    0.85
    №
    0.85
    user
    0.84
    索引
    0.79
    0.78
    self
    0.78
    max
    0.78
    maximum
    0.78
    子
    0.76
    Activations Density 0.019%

    No Known Activations