© 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. 65274
    Prev
    Next
    INDEX
    Explanations

    numbers and line indicators

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

    The neuron detects numeric timestamp fragments (two‐ or three‐digit numbers used in timecodes/log markers).

    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
    feest
    -0.85
     Savoie
    -0.85
     intim
    -0.84
    upu
    -0.79
     smör
    -0.78
    sheet
    -0.77
    fontFamily
    -0.77
    CLU
    -0.76
    SimpleName
    -0.75
     hispan
    -0.75
    POSITIVE LOGITS
    Scher
    0.93
     how
    0.92
    ühle
    0.88
     including
    0.87
     Reading
    0.87
     Vous
    0.86
     rústica
    0.86
     hosszú
    0.85
    izop
    0.85
     Deputies
    0.84
    Activations Density 0.007%

    No Known Activations