© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45490
    Prev
    Next
    INDEX
    Explanations

    numbers and labels

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

    The neuron responds to numeric tokens—that is, sequences of digits representing numbers.

    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
    quic
    -0.84
    Their
    -0.80
    ajte
    -0.78
    HV
    -0.78
    /*/
    -0.75
     måde
    -0.75
    panes
    -0.75
    ]");
    -0.75
    
    -0.74
    stof
    -0.74
    POSITIVE LOGITS
    hydrop
    0.81
     into
    0.71
     едино
    0.70
    スパイ
    0.69
    sigh
    0.69
     Demp
    0.68
    私に
    0.67
    ؤية
    0.66
    пев
    0.66
    льный
    0.66
    Activations Density 0.000%

    No Known Activations