© 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. 22-GEMMASCOPE-RES-131K
    7. 33103
    Prev
    Next
    INDEX
    Explanations

    research methodologies and approaches

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

    The neuron fires on the principal content words (nouns, verbs, and adjectives) characteristic of formal academic prose.

    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
    に於
    -1.44
    Extrait
    -1.38
    夕食
    -1.38
    tablissements
    -1.36
    全体の
    -1.34
     inimes
    -1.34
     when
    -1.34
     menyimpan
    -1.26
    Transkript
    -1.25
    ).
    -1.24
    POSITIVE LOGITS
    最近
    1.38
    larg
    1.34
    contentPadding
    1.32
    וּ
    1.29
    zensionen
    1.29
    Refreshing
    1.28
    它
    1.27
     предмет
    1.25
     WaitForSeconds
    1.25
     inqu
    1.23
    Activations Density 0.097%

    No Known Activations