© 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. 38775
    Prev
    Next
    INDEX
    Explanations

    vacantion destinations and venues

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

    The neuron primarily detects mentions of resort and hotel brand names (including vacation clubs) and related proper‐noun property names.

    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
    4
    -1.05
    wości
    -1.03
    palen
    -1.02
    lenen
    -1.01
     lievito
    -1.01
     attacc
    -0.99
    kå
    -0.97
    %;
    -0.97
     so
    -0.97
     加载
    -0.96
    POSITIVE LOGITS
     here
    1.40
    筈
    1.16
     dozen
    1.12
     ổ
    1.12
     your
    1.11
     incluso
    1.05
    さまざま
    1.04
    ったのは
    1.03
     even
    1.02
                
    1.01
    Activations Density 0.054%

    No Known Activations