© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10470
    Prev
    Next
    INDEX
    Explanations

    enumerated sections and parts

    np_acts-logits-general · gemini-2.5-flash-lite

    step item part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    ⇵
    0.41
    𝙇
    0.40
     SHEET
    0.40
    ંભ
    0.38
    Verbose
    0.36
     contractName
    0.36
     ALERT
    0.36
    uşt
    0.36
    𝙄
    0.35
    უალ
    0.35
    POSITIVE LOGITS
     subparagraph
    0.78
     b
    0.77
    ⑴
    0.74
    a
    0.70
    iii
    0.68
     iii
    0.63
    panels
    0.62
    parts
    0.61
    panel
    0.61
    ⑵
    0.61
    Activations Density 0.165%

    No Known Activations