© 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. 7506
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

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

    The neuron is looking for occurrences of the substring “mav” (as in MAVLink message identifiers).

    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
    ’
    -3.16
     He
    -2.13
    或是
    -2.11
    y
    -2.09
     weiteres
    -2.08
    ies
    -1.96
    ୃ
    -1.96
     refiere
    -1.95
     keduanya
    -1.83
    6
    -1.83
    POSITIVE LOGITS
    Ｔ
    2.33
    )$
    2.31
     he
    2.25
     starb
    2.25
    ㆍ
    2.20
    镚
    2.20
    {\
    2.16
    สำหรับ
    2.14
    してみると
    2.14
    ď
    2.11
    Activations Density 0.000%

    No Known Activations