© 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. 25324
    Prev
    Next
    INDEX
    Explanations

    Already

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

    The neuron is looking for standalone numeric references (e.g. “including time served,” assembler “.align 1,” list items like “this one is …,” etc.).

    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
    ritis
    -0.77
    ものです
    -0.76
     cortesía
    -0.75
    程度の
    -0.75
     Produced
    -0.73
    ProductType
    -0.72
     sopa
    -0.72
    たた
    -0.70
    )—
    -0.70
    داية
    -0.70
    POSITIVE LOGITS
     already
    3.97
    Already
    3.00
     уже
    2.97
    already
    2.92
     już
    2.77
     вже
    2.72
     Already
    2.67
     allerede
    2.42
    已经
    2.38
     già
    2.34
    Activations Density 0.053%

    No Known Activations