© 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. 16201
    Prev
    Next
    INDEX
    Explanations

    push into

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

    The neuron activates specifically on the word “push” (and its inflected forms like “pushes,” “pushed,” “pushing”).

    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
     there
    -0.97
     when
    -0.96
    这里是
    -0.95
     after
    -0.94
    There
    -0.90
     contemplar
    -0.90
    OREA
    -0.90
    ***/
    -0.89
    ͓
    -0.88
     will
    -0.85
    POSITIVE LOGITS
     into
    2.70
     toward
    1.66
     onto
    1.61
     towards
    1.59
    pushed
    1.27
     against
    1.24
    toward
    1.11
     Pushing
    1.09
    Into
    1.09
     Into
    1.07
    Activations Density 0.034%

    No Known Activations