© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1078
    Prev
    Next
    INDEX
    Explanations

    asking me to understand or assist

    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_7_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
    okatokat
    1.96
     htob
    1.88
     उनकी
    1.87
     kttt
    1.87
    ExpNow
    1.85
     všetky
    1.84
    𐰼
    1.83
     filha
    1.83
     njegova
    1.83
     rotacao
    1.82
    POSITIVE LOGITS
    .
    1.67
    '
    1.42
    -
    1.39
     style
    1.29
    ogical
    1.25
     aesthetic
    1.23
    style
    1.21
    sp
    1.20
    ian
    1.18
    lass
    1.18
    Activations Density 0.924%

    No Known Activations