© 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. 72783
    Prev
    Next
    INDEX
    Explanations

    free access and information

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

    The neuron fires on marketing- or advice-style calls to action addressed to “you,” i.e. promotional/imperative phrases encouraging the reader to do something.

    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
     however
    -1.29
     azonban
    -1.13
     these
    -1.10
    _
    -1.09
     kuitenkin
    -1.03
     však
    -0.98
     yapılır
    -0.96
     però
    -0.93
     nämlich
    -0.92
    قول
    -0.92
    POSITIVE LOGITS
    啻
    1.07
     ถ้า
    1.04
     thereof
    1.00
     играть
    1.00
     —
    0.97
    télé
    0.92
    hébergement
    0.89
    small
    0.89
     söyledi
    0.88
    tira
    0.88
    Activations Density 0.103%

    No Known Activations