© 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. 79153
    Prev
    Next
    INDEX
    Explanations

    cache memory misses and locality

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

    The neuron fires on numeric tokens, identifying numbers (e.g. values in XML attributes or standalone digits) in the text.

    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
     мебель
    -0.75
    дации
    -0.73
     enlace
    -0.73
    źródło
    -0.73
    Жан
    -0.73
     Arithmetic
    -0.73
    LECTION
    -0.72
    กิ
    -0.72
    stun
    -0.72
     Sanford
    -0.72
    POSITIVE LOGITS
     misses
    1.25
     miss
    1.23
     cache
    1.07
     Miss
    1.05
    miss
    1.01
    associ
    1.01
     associ
    0.98
    MISS
    0.96
     line
    0.93
    Associ
    0.93
    Activations Density 0.019%

    No Known Activations