© 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. 100193
    Prev
    Next
    INDEX
    Explanations

    channel inner thoughts or expressions

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

    The neuron detects occurrences of the word “channel” (and its morphological variants like “channeling”).

    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
    quirer
    -1.49
     admiten
    -1.48
    cologist
    -1.46
    titial
    -1.46
     keuze
    -1.45
     inyección
    -1.45
     informaron
    -1.45
     estabiliz
    -1.45
     najdete
    -1.44
     considération
    -1.43
    POSITIVE LOGITS
    <tbody>
    1.48
     an
    1.29
     ALL
    1.28
     жовтня
    1.26
     traditional
    1.25
     As
    1.23
     mina
    1.21
     religi
    1.20
    чих
    1.20
     sobre
    1.20
    Activations Density 0.037%

    No Known Activations