© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68206
    Prev
    Next
    INDEX
    Explanations

    continual such as used there Sony vibration

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

    The neuron detects numeric tokens—numbers and numeric values like dates, statistics, or measurements.

    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
     Když
    -0.93
     Colomb
    -0.91
    acca
    -0.88
     Когда
    -0.88
     afbeelding
    -0.88
    fta
    -0.88
    ヴ
    -0.86
    可以让
    -0.85
    还不是
    -0.85
    ARAN
    -0.84
    POSITIVE LOGITS
     also
    1.19
     this
    1.12
    {{/
    1.02
    メニューは
    0.96
     there
    0.94
     now
    0.93
    welijk
    0.92
     these
    0.91
     your
    0.91
     on
    0.91
    Activations Density 0.005%

    No Known Activations