© 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. 122
    Prev
    Next
    INDEX
    Explanations

    multi-lingual data structures

    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
     monthly
    0.61
     Monthly
    0.59
     ∈
    0.59
     Frontier
    0.58
     Plot
    0.58
     bubble
    0.58
     (%)
    0.58
     |
    0.58
     dec
    0.57
     belly
    0.57
    POSITIVE LOGITS
    <unused63>
    0.87
    <unused62>
    0.84
     Allard
    0.82
     sintomas
    0.81
     iskol
    0.79
    <unused0>
    0.79
     menyebabkan
    0.79
    மஹ
    0.78
    <unused61>
    0.78
    etsch
    0.76
    Activations Density 0.030%

    No Known Activations