© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99727
    Prev
    Next
    INDEX
    Explanations

    block of

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

    The neuron is specialized to detect numeric tokens (e.g. digits in addresses, block numbers, dates, money amounts).

    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
    ूह
    -0.79
    𝘶
    -0.79
     wretch
    -0.77
    pektrum
    -0.75
     whereby
    -0.75
    ᪥
    -0.74
     摄影
    -0.74
    erjee
    -0.73
     stylus
    -0.73
    Vendo
    -0.73
    POSITIVE LOGITS
     block
    2.28
    block
    1.69
     Block
    1.60
     blocks
    1.55
    blk
    1.38
    Block
    1.34
     BLOCK
    1.32
     bloc
    1.26
     Blocks
    1.23
     blok
    1.20
    Activations Density 0.008%

    No Known Activations