© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14101
    Prev
    Next
    INDEX
    Explanations

    looking forward to + action

    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
    ,
    1.46
     addicted
    1.19
     crianças
    1.09
     better
    1.08
     fatt
    1.07
    outine
    1.07
     cintura
    1.07
     children
    1.07
     un
    1.05
     marries
    1.04
    POSITIVE LOGITS
    笏
    1.89
     Gebäude
    1.81
    ਲੇ
    1.81
    nPort
    1.81
    lEdit
    1.78
    gebäude
    1.76
    atribut
    1.74
     террито
    1.73
    िलेश
    1.73
    <unused1694>
    1.72
    Activations Density 0.110%

    No Known Activations