© 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. 82809
    Prev
    Next
    INDEX
    Explanations

    degree intensifiers

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

    The neuron is detecting numeric literals—especially version numbers, configuration values, and other digits—in code and documentation.

    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
     so
    -1.35
     with
    -1.28
     from
    -1.26
     because
    -1.23
     just
    -1.20
     at
    -1.20
     after
    -1.16
     before
    -1.12
     on
    -1.11
     While
    -1.10
    POSITIVE LOGITS
     insanely
    1.34
     horrid
    1.23
     absurd
    1.23
     ridiculously
    1.22
     exceptionally
    1.18
     exceedingly
    1.16
     deliciously
    1.12
     unbelievably
    1.09
     incredibly
    1.08
     idiotic
    1.08
    Activations Density 0.004%

    No Known Activations