© 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. 129422
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for third-person singular present-tense stative or fact-stating verbs (e.g. “has,” “produces,” “offers”) that introduce descriptive or factual statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    such examples of quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ervaring
    -1.13
     vrijdag
    -1.10
     reacties
    -1.09
     omgeving
    -1.07
     wła
    -1.06
     ameryka
    -1.05
     ešte
    -1.04
     themselves
    -1.04
    ыргыз
    -1.02
     vaše
    -1.02
    POSITIVE LOGITS
     its
    2.17
    Its
    1.97
     Its
    1.44
    它的
    1.44
    its
    1.13
     rique
    1.01
     таких
    1.01
     a
    1.00
     μόνο
    1.00
    ///<
    0.99
    Activations Density 0.092%

    No Known Activations