© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 876
    Prev
    Next
    INDEX
    Explanations

    crucial/crucially

    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
    '
    1.28
    ’
    1.10
    ʼ
    0.92
    ʻ
    0.83
    ’
    0.80
    `
    0.79
    ´
    0.76
     voluptate
    0.70
    &#
    0.70
    <0x19>
    0.69
    POSITIVE LOGITS
     ਤੇ
    1.08
    baar
    0.93
    რივ
    0.92
    ISATION
    0.89
    IZATION
    0.85
    링
    0.84
    PLEX
    0.83
    ਤੇ
    0.82
    िंग
    0.82
    ization
    0.81
    Activations Density 0.545%

    No Known Activations