© 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. 34-GEMMASCOPE-RES-131K
    7. 117213
    Prev
    Next
    INDEX
    Explanations

    Search in

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

    The neuron activates specifically on standalone numeric tokens (strings of digits).

    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
     on
    -1.46
     for
    -1.41
     just
    -1.34
     in
    -1.26
     or
    -1.22
     over
    -1.14
     high
    -1.12
     so
    -1.10
     their
    -1.09
     one
    -1.05
    POSITIVE LOGITS
     passende
    1.07
     molte
    1.05
     zoude
    1.04
     idiotic
    1.02
     alcune
    1.02
     ſol
    1.01
    
    1.00
     konkrét
    1.00
     recepción
    0.99
     firs
    0.99
    Activations Density 0.000%

    No Known Activations