© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35205
    Prev
    Next
    INDEX
    Explanations

    Category numbers and names

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

    The neuron activates on numeric tokens, i.e. sequences of digits appearing 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_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
     these
    -1.45
     here
    -1.28
     this
    -1.27
    ditionally
    -1.26
    せっかく
    -1.22
     花朵
    -1.19
    obut
    -1.18
    妩
    -1.18
    complish
    -1.14
    が違う
    -1.14
    POSITIVE LOGITS
     etc
    1.28
     ausreichend
    1.09
    一年
    1.00
     incluir
    0.98
    入れて
    0.98
    johnson
    0.96
     aktuelle
    0.96
    各种
    0.95
     Strong
    0.95
    就知道
    0.95
    Activations Density 0.005%

    No Known Activations