© 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. 67836
    Prev
    Next
    INDEX
    Explanations

    label followed by colon or equals

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

    The neuron is detecting the “-->” time‐range arrow marker used in subtitle (SRT) timestamp lines.

    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
    1
    -3.48
    6
    -2.72
    0
    -2.66
    3
    -2.63
    8
    -2.53
    4
    -2.52
    2
    -2.44
    9
    -2.39
    5
    -2.16
    "
    -2.14
    POSITIVE LOGITS
    งิน
    2.30
    のこと
    1.98
     urme
    1.95
    骐
    1.88
    喩
    1.87
    椅子
    1.85
     who
    1.83
    谵
    1.82
     legislat
    1.76
    ↵
    1.75
    Activations Density 0.000%

    No Known Activations