© 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. 22-GEMMASCOPE-2-RES-16K
    7. 369
    Prev
    Next
    INDEX
    Explanations

    possessive 's or 't

    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
    ll
    0.46
    s
    0.45
    re
    0.37
    ve
    0.35
    d
    0.35
     s
    0.34
     ll
    0.34
     ve
    0.32
     in
    0.31
     re
    0.30
    POSITIVE LOGITS
    𐰀
    0.67
    ྞ
    0.66
    Bechyné
    0.64
    ཋ
    0.64
    𒁹
    0.64
    𒆳
    0.64
    𒃻
    0.64
    𒅎
    0.63
    𒉈
    0.63
    𒊩
    0.62
    Activations Density 1.204%

    No Known Activations