© 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. 10-GEMMASCOPE-RES-131K
    7. 13137
    Prev
    Next
    INDEX
    Explanations

    left sidebar or menu

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

    The neuron detects words referring to user‐interface panel locations or directions (e.g. “left,” “right,” “pane,” “hand”).

    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
     begin
    -1.70
     Schluß
    -1.55
     be
    -1.53
     Bewußt
    -1.52
     to
    -1.47
     teilweise
    -1.47
     his
    -1.45
     that
    -1.43
     Also
    -1.42
    istiques
    -1.42
    POSITIVE LOGITS
    where
    1.85
    らなかった
    1.45
     этих
    1.43
    Embal
    1.37
     apport
    1.36
    鷽
    1.35
     Songtext
    1.34
     spéc
    1.33
     feit
    1.33
     chini
    1.32
    Activations Density 0.035%

    No Known Activations