© 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. 25768
    Prev
    Next
    INDEX
    Explanations

    situations and events

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

    This neuron detects words signaling preparation or anticipation for an upcoming event.

    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
    LANDS
    -0.96
     sere
    -0.96
    Feuer
    -0.96
     havde
    -0.94
    िक्ष
    -0.94
     siden
    -0.94
    Dettagli
    -0.93
     RECOMMEND
    -0.92
     paperback
    -0.92
    Pao
    -0.91
    POSITIVE LOGITS
     trying
    1.07
     just
    1.02
     in
    1.01
     în
    1.00
     what
    0.94
    ak
    0.93
    ksikon
    0.91
     into
    0.90
     What
    0.90
    R
    0.90
    Activations Density 0.011%

    No Known Activations