© 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. 10-GEMMASCOPE-RES-131K
    7. 41147
    Prev
    Next
    INDEX
    Explanations

    verbs indicating achievement or completion

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

    The main thing this neuron does is detect numeric tokens or quantitative values (e.g. digits and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.05
    They
    -1.55
    However
    -1.55
     as
    -1.49
    Mereka
    -1.43
     at
    -1.43
     on
    -1.42
     increases
    -1.41
     They
    -1.39
    Some
    -1.39
    POSITIVE LOGITS
     pouze
    1.58
    !!!!!!!
    1.51
    -[
    1.50
     prawie
    1.46
    (=
    1.44
    ılık
    1.41
     trám
    1.41
    莛
    1.41
    !!!!!!
    1.40
     várias
    1.36
    Activations Density 0.044%

    No Known Activations