© 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. 17-GEMMASCOPE-2-RES-16K
    7. 191
    Prev
    Next
    INDEX
    Explanations

    Core Count or device count

    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_17_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
    -
    0.80
    /
    0.65
    ,
    0.62
    .
    0.57
     inte
    0.57
    :
    0.55
     …,
    0.55
    ]
    0.53
     …
    0.53
     not
    0.52
    POSITIVE LOGITS
    s
    1.12
    sini
    1.06
     Anakin
    1.01
     Kanye
    0.99
    tattoo
    0.99
     Beyonce
    0.98
     heartbroken
    0.98
    sop
    0.97
     Beyoncé
    0.97
    sia
    0.96
    Activations Density 0.948%

    No Known Activations