© 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. 10-GEMMASCOPE-RES-131K
    7. 45133
    Prev
    Next
    INDEX
    Explanations

    carriage return

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

    The neuron fires on the “r” of “\r” escape sequences—i.e. it detects carriage‐return characters in 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_10/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
     utterly
    -2.09
     profoundly
    -2.02
     establish
    -1.95
     fierce
    -1.95
    '
    -1.89
     superbly
    -1.88
     promote
    -1.87
     remove
    -1.87
     markedly
    -1.85
     horrific
    -1.85
    POSITIVE LOGITS
    戗
    2.39
     the
    2.28
    鱨
    2.27
    냑
    2.25
     REALLY
    2.25
     nonchal
    2.23
    感觉到
    2.22
    ᴎ
    2.20
    they
    2.19
     astonishing
    2.19
    Activations Density 0.001%

    No Known Activations