© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43404
    Prev
    Next
    INDEX
    Explanations

    data communication and transmission

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

    The neuron activates on technical telecommunications jargon—especially mentions of “data,” “voice,” “communication,” and related signal-capacity terms.

    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
     mesma
    -1.39
    媜
    -1.36
    ════
    -1.26
     intérprete
    -1.21
    ON
    -1.18
     mooie
    -1.17
    酲
    -1.16
    ѫ
    -1.16
    側の
    -1.16
     you
    -1.16
    POSITIVE LOGITS
    In
    1.60
    ﾖ
    1.45
    檸檬
    1.44
    When
    1.40
    Regarding
    1.37
    %",
    1.36
    =('
    1.33
    طول
    1.31
    ложении
    1.30
    ᗜ
    1.30
    Activations Density 0.115%

    No Known Activations