© 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. 34-GEMMASCOPE-RES-131K
    7. 107900
    Prev
    Next
    INDEX
    Explanations

    is especially or is particularly

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

    The neuron fires strongly on occurrences of the phrase “This is,” i.e. sentences beginning with “This is” as a definitional or introductory clause.

    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
    suchen
    -1.27
     этого
    -1.23
    här
    -1.19
    beschreibung
    -1.13
    kommt
    -1.12
     gitara
    -1.11
    ocuk
    -1.10
     этих
    -1.09
    billon
    -1.09
    wirk
    -1.08
    POSITIVE LOGITS
     why
    2.75
     because
    2.36
     especially
    1.98
     particularly
    1.89
     where
    1.80
     how
    1.79
     to
    1.66
     despite
    1.66
     then
    1.62
     true
    1.48
    Activations Density 0.073%

    No Known Activations