© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14105
    Prev
    Next
    INDEX
    Explanations

    lose sight of

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

    The neuron selectively activates on second-person pronouns (especially “you” and “your”) and nearby directive or advisory 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
     recent
    -1.47
     would
    -1.35
    Ἡ
    -1.30
    などなど
    -1.29
    recent
    -1.24
     avenir
    -1.21
     NIGERIA
    -1.21
    ͚
    -1.19
     laik
    -1.18
     harap
    -1.16
    POSITIVE LOGITS
     [
    1.73
     people
    1.70
     what
    1.69
     somebody
    1.63
     our
    1.45
     things
    1.43
     someone
    1.40
     you
    1.33
     different
    1.27
    ほうが
    1.27
    Activations Density 0.010%

    No Known Activations