© 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. 22-GEMMASCOPE-RES-131K
    7. 26730
    Prev
    Next
    INDEX
    Explanations

    reporting news or asking questions

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

    The neuron fires on language giving advice or recommendations—phrases framed as “what you should…” or similar second-person directives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Both
    -1.12
     it
    -1.10
     oczywiście
    -1.02
    ところに
    -1.02
    ريكي
    -0.98
     top
    -0.96
     there
    -0.96
    奬
    -0.94
     last
    -0.94
     two
    -0.94
    POSITIVE LOGITS
    лять
    1.14
    pherals
    1.13
     familien
    1.07
     Resmi
    1.01
     temen
    1.01
    ﹒
    0.97
    谁
    0.95
    FLICT
    0.93
     sommeil
    0.93
    сение
    0.93
    Activations Density 0.090%

    No Known Activations