© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    verbs ending in s or es

    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
    ed
    3.76
    ة
    3.04
    ED
    2.73
    edm
    2.05
    edf
    2.02
    Ed
    1.88
     Ed
    1.85
    edel
    1.78
     ED
    1.73
    edk
    1.72
    POSITIVE LOGITS
    𝓷
    1.04
    𝓭
    1.03
    भारी
    1.01
    mest
    1.00
    어진
    0.98
     Однако
    0.97
    รัฐ
    0.96
    יית
    0.93
    AnimationFrame
    0.92
    ❯
    0.92
    Activations Density 0.286%

    No Known Activations