© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130907
    Prev
    Next
    INDEX
    Explanations

    finding sources for details

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

    The neuron flags words that introduce pointers to further information or references—terms like “details,” “more,” “information,” “definitions,” or “detailed” in “For … see” or “For … on” style phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     anuncia
    -1.40
     a
    -1.40
     coment
    -1.39
     compared
    -1.35
     потому
    -1.34
    谢谢你
    -1.32
    mands
    -1.30
    itively
    -1.30
    alties
    -1.28
     tyto
    -1.27
    POSITIVE LOGITS
    $,
    1.58
     which
    1.54
    }$,
    1.48
    )$,
    1.48
    (),
    1.45
     please
    1.44
     whose
    1.39
    ”,
    1.36
     yourself
    1.34
     اینکه
    1.30
    Activations Density 0.057%

    No Known Activations