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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7357
    Prev
    Next
    INDEX
    Explanations

    roll, rolling, rollout, rollback

    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
    údo
    1.11
    dig
    1.08
    획
    1.01
     enig
    0.98
    Resolution
    0.97
     disag
    0.97
    ग्विजय
    0.96
     जिज्ञासा
    0.95
    हदी
    0.95
     resolution
    0.95
    POSITIVE LOGITS
    coaster
    1.20
     coaster
    1.14
     Royce
    1.13
     hills
    1.04
     dice
    1.00
    bahn
    1.00
    滚
    0.99
     shutters
    0.98
    eston
    0.96
    滚动
    0.96
    Activations Density 0.089%

    No Known Activations