© 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. 107196
    Prev
    Next
    INDEX
    Explanations

    common occurrences

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

    The neuron fires on the word “common” (and its close variants) when it’s used to indicate something’s prevalence or frequency.

    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
     расположен
    -0.90
    blob
    -0.85
    ANSION
    -0.84
     speechless
    -0.82
    thral
    -0.79
    万人
    -0.79
    siers
    -0.78
     hormigón
    -0.78
     minded
    -0.77
    SPAN
    -0.77
    POSITIVE LOGITS
     place
    2.55
    place
    2.28
     occurrence
    2.23
    Place
    1.89
    PLACE
    1.83
     occurrences
    1.81
     Place
    1.60
    occurrence
    1.55
     lugar
    1.43
     PLACE
    1.41
    Activations Density 0.039%

    No Known Activations