© 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. 34-GEMMASCOPE-RES-131K
    7. 91736
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron is detecting numeric tokens (digits or multi‐digit numbers) such as version numbers or numeric constants in code and other documents.

    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
     an
    -1.25
     his
    -1.23
     one
    -1.20
     sizeable
    -1.04
     many
    -1.02
     sizable
    -1.02
     retten
    -1.00
     extraordinarily
    -0.99
     a
    -0.98
     getting
    -0.98
    POSITIVE LOGITS
     ardu
    1.22
     telefónica
    1.21
     benevol
    1.20
    を購入
    1.16
     imme
    1.08
    」
    1.08
     ines
    1.07
    必须
    1.06
     inev
    1.05
     bancaria
    1.05
    Activations Density 0.153%

    No Known Activations