© 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. 33941
    Prev
    Next
    INDEX
    Explanations

    credibility, reputation, and feelings

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

    This neuron responds to tokens in direct reader-address/advice contexts—especially second-person (“you,” “your”) and related guidance phrasing.

    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
     liquide
    -1.20
     astu
    -1.20
     palab
    -1.11
     bronz
    -1.07
     garan
    -1.07
    elum
    -1.07
     malgré
    -1.05
    鸨
    -1.05
     chien
    -1.04
     téléph
    -1.04
    POSITIVE LOGITS
     reputation
    1.57
     longstanding
    1.28
     people
    1.27
     future
    1.19
     any
    1.19
     establishing
    1.18
     futuras
    1.14
     two
    1.13
     credibility
    1.09
     friends
    1.08
    Activations Density 0.022%

    No Known Activations