© 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. 99919
    Prev
    Next
    INDEX
    Explanations

    channel id and type

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

    This neuron fires on the token “channel” (or variants containing that substring), regardless of context.

    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
    </h3>
    -2.09
     也
    -2.00
    pagnols
    -1.96
    ቷ
    -1.95
     also
    -1.91
     was
    -1.88
     ferrovia
    -1.88
     スクール
    -1.88
     recensione
    -1.78
     solidari
    -1.77
    POSITIVE LOGITS
    \
    2.48
    </b>
    2.19
     were
    2.08
     Channels
    2.08
    channel
    2.02
    ᎒
    1.95
     purport
    1.95
    )),
    1.91
    }$,
    1.88
     guten
    1.88
    Activations Density 0.016%

    No Known Activations