© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1914
    Prev
    Next
    INDEX
    Explanations

    were leased

    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_17_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
    BibitemShut
    0.90
    insic
    0.84
    ージー
    0.83
    зья
    0.79
    ƾ
    0.78
    讃
    0.78
    రువు
    0.78
    蹙
    0.78
    <unused2109>
    0.77
    शेदपुर
    0.76
    POSITIVE LOGITS
     LS
    2.56
     LC
    2.51
    LS
    2.46
     LH
    2.46
    LC
    2.46
     LI
    2.43
     LM
    2.41
     LU
    2.40
    L
    2.38
     LB
    2.37
    Activations Density 1.942%

    No Known Activations