© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128972
    Prev
    Next
    INDEX
    Explanations

    up or down to

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

    The neuron selectively activates on simple directional adverbs (e.g. “down,” “up,” “out”) indicating motion or extent.

    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
     also
    -2.92
     for
    -2.42
     in
    -2.30
     and
    -2.25
     like
    -2.22
     as
    -2.14
     of
    -2.13
     it
    -2.09
     by
    -1.98
     with
    -1.98
    POSITIVE LOGITS
    鹀
    2.56
    ⸂
    2.30
    嵓
    2.16
    ⩖
    2.14
    
    2.13
    聽到
    2.09
     anunció
    2.06
     использовании
    2.06
     spezi
    2.06
    ,”
    2.06
    Activations Density 0.046%

    No Known Activations