© 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. 7859
    Prev
    Next
    INDEX
    Explanations

    github links

    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
    e
    1.77
    er
    1.66
    ر
    1.63
    ea
    1.61
    eis
    1.58
    ी
    1.56
    o
    1.55
    ه
    1.55
    eck
    1.52
    eek
    1.52
    POSITIVE LOGITS
    另一
    1.06
    ributedString
    1.02
    另
    0.99
    ಗರ
    0.98
     άλλο
    0.96
    माटर
    0.95
    ות
    0.95
    γά
    0.94
    ותו
    0.93
     ảnh
    0.93
    Activations Density 0.126%

    No Known Activations