© 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. 34-GEMMASCOPE-RES-131K
    7. 2714
    Prev
    Next
    INDEX
    Explanations

    object recognition and detection

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

    This neuron detects occurrences of the term “stance” (particularly in the context of news or stance‐detection titles and keywords).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Geruch
    -0.82
     stupid
    -0.79
     roupa
    -0.77
     Deak
    -0.76
     evident
    -0.75
    datal
    -0.73
    ondata
    -0.73
     Managing
    -0.72
     techniques
    -0.71
    queira
    -0.71
    POSITIVE LOGITS
    Aware
    0.91
    aware
    0.88
     modeling
    0.84
    Understanding
    0.81
     ESTIM
    0.79
    до
    0.79
     modelling
    0.78
     antibio
    0.77
     опи
    0.77
     Foer
    0.77
    Activations Density 0.073%

    No Known Activations