© 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. 7676
    Prev
    Next
    INDEX
    Explanations

    patents and legal execution

    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
    یو
    1.06
    洌
    0.94
    禊
    0.94
    ِد
    0.92
    Sett
    0.91
    ِل
    0.91
    𝙨
    0.90
    酔
    0.89
    yst
    0.88
    sy
    0.88
    POSITIVE LOGITS
     chances
    1.00
    ==============]
    0.95
     raincoat
    0.90
     nuclé
    0.90
     chance
    0.89
     aço
    0.87
    Elastic
    0.86
    动手
    0.85
     Crane
    0.84
     Linen
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.