© 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. 10-GEMMASCOPE-RES-131K
    7. 38896
    Prev
    Next
    INDEX
    Explanations

    to destination

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

    The neuron strongly activates on words denoting a change of state or movement from one thing to another (e.g. “transferred,” “transitioned”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    cisive
    -2.16
     
    -1.90
    甃
    -1.89
    formatics
    -1.83
     môžete
    -1.72
     houſe
    -1.72
    hibited
    -1.70
    
    -1.69
    ventions
    -1.66
    consola
    -1.63
    POSITIVE LOGITS
     a
    2.39
     using
    2.02
     another
    1.95
     an
    1.92
     from
    1.90
     Another
    1.88
     our
    1.80
     interestingly
    1.77
     impressively
    1.73
     were
    1.70
    Activations Density 0.062%

    No Known Activations