© 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. 26413
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron detects words and phrases that mark location or proximity (e.g. “ideally,” “located,” “a few,” directional/place names) in venue descriptions.

    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
     like
    -1.45
     about
    -1.10
    dina
    -1.03
    だから
    -1.02
     that
    -1.02
    大さじ
    -0.98
     just
    -0.96
    arcas
    -0.96
     to
    -0.94
    čili
    -0.93
    POSITIVE LOGITS
    reiches
    1.20
     также
    1.19
     Furthermore
    1.16
     apabila
    1.16
    Также
    1.15
    Suspicious
    1.13
    Преимущества
    1.13
     年级
    1.09
    Ingrédients
    1.09
     również
    1.09
    Activations Density 0.000%

    No Known Activations