© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93492
    Prev
    Next
    INDEX
    Explanations

    web links and licensing terms

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

    The neuron selectively activates on numeric literals (digits and multi‐digit number tokens) in the 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_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
    zell
    -0.65
     peruana
    -0.65
     النها
    -0.64
     CAPT
    -0.63
    ienna
    -0.61
    Cheer
    -0.61
     pager
    -0.60
    ;<
    -0.60
    ffichage
    -0.59
    adhé
    -0.59
    POSITIVE LOGITS
    iroz
    0.80
    まれる
    0.78
     Boy
    0.74
    끈
    0.69
     Gene
    0.67
     instalado
    0.66
    Particle
    0.65
    腸
    0.64
    ığımız
    0.63
    烏
    0.63
    Activations Density 0.080%

    No Known Activations