© 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. 700
    Prev
    Next
    INDEX
    Explanations

    people's struggles and impacts

    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
     bricks
    2.02
     that
    1.82
     of
    1.82
     and
    1.74
     goodwill
    1.72
     craving
    1.72
     ο
    1.69
     capitalist
    1.68
     cruel
    1.67
     coins
    1.63
    POSITIVE LOGITS
    addGap
    2.20
    ोले
    2.16
    itiert
    2.14
    łożyć
    2.14
    ilé
    2.13
    etään
    2.13
    lebihan
    2.11
    ępuje
    2.10
     reconoce
    2.07
    ᐟ
    2.07
    Activations Density 0.005%

    No Known Activations