© 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. 34-GEMMASCOPE-RES-131K
    7. 97732
    Prev
    Next
    INDEX
    Explanations

    code comments and license texts

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

    The neuron specifically activates on numeric tokens (especially multi‐digit numbers like years or other numeric literals).

    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
     wybrać
    -1.02
     uzyskać
    -0.88
     стене
    -0.88
     двери
    -0.87
    CCION
    -0.85
    了一会儿
    -0.84
     NACIONAL
    -0.82
     Ion
    -0.82
     derive
    -0.81
     announce
    -0.81
    POSITIVE LOGITS
    ल्स
    1.07
     prosegu
    1.04
    Matéri
    0.97
    zelfde
    0.94
     stesse
    0.94
     sepol
    0.94
    gleiche
    0.93
    還可以
    0.93
    NgModule
    0.92
    Ors
    0.91
    Activations Density 0.000%

    No Known Activations