Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8689
    Prev
    Next
    INDEX
    Explanations

    taking notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIP
    -0.88
    meri
    -0.84
    rle
    -0.84
    を与
    -0.83
    omation
    -0.83
    ternos
    -0.82
    Mailbox
    -0.82
    δικ
    -0.81
    袭击
    -0.81
     Newsletters
    -0.80
    POSITIVE LOGITS
     notes
    3.83
    notes
    3.05
     Notes
    2.73
    Notes
    2.70
     note
    2.70
     NOTES
    2.28
    note
    2.22
    笔记
    2.22
    NOTES
    2.19
     jot
    1.98
    Activations Density 0.032%

    No Known Activations