© 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. 117713
    Prev
    Next
    INDEX
    Explanations

    teaching and learning

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

    The neuron fires strongly on content words in formal academic or scientific‐article writing (e.g. in abstracts and methods sections).

    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
     teknis
    -1.27
     firft
    -1.23
     REGIONAL
    -1.16
    accéder
    -1.16
     kompeti
    -1.13
     Meksiko
    -1.13
    Примеча
    -1.09
     occafion
    -1.08
     datter
    -1.07
    editary
    -1.05
    POSITIVE LOGITS
     teachers
    2.41
     teacher
    2.38
     students
    2.25
     classroom
    2.05
     student
    1.82
     learners
    1.80
    teacher
    1.70
     learner
    1.69
     Teachers
    1.67
    Teachers
    1.63
    Activations Density 0.034%

    No Known Activations