© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67527
    Prev
    Next
    INDEX
    Explanations

    have storage access

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

    The neuron detects “requirements” or “prerequisite” statements (e.g. lines specifying needed software versions or packages).

    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
     mostly
    -1.34
     sometimes
    -1.25
     also
    -1.24
     найден
    -1.20
     didn
    -1.20
     "
    -1.19
     too
    -1.18
     about
    -1.18
     usually
    -1.16
     Üniversitesi
    -1.12
    POSITIVE LOGITS
    сезон
    1.26
    guigu
    1.24
    conut
    1.20
    tribune
    1.16
     تجمعات
    1.16
    bnf
    1.16
    huawei
    1.16
    ciri
    1.13
    そのような
    1.11
     compreender
    1.08
    Activations Density 0.170%

    No Known Activations