© 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. 153
    Prev
    Next
    INDEX
    Explanations

    apostrophe s

    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
    ledes
    0.72
    呔
    0.72
    andelions
    0.72
     गरेका
    0.71
    மையும்
    0.71
    vised
    0.71
     permiss
    0.70
    ेलो
    0.70
    маш
    0.69
    mathspace
    0.68
    POSITIVE LOGITS
    s
    2.12
    sG
    1.60
    ｓ
    1.58
     s
    1.51
    𝐬
    1.47
    S
    1.46
    𝒔
    1.46
    𝑠
    1.42
    ѕ
    1.39
    ्स
    1.39
    Activations Density 1.867%

    No Known Activations