© 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. 78052
    Prev
    Next
    INDEX
    Explanations

    skill or ability

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

    The neuron flags numeric tokens—especially integer values—wherever they occur.

    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
    ension
    -0.83
    련
    -0.81
    Schedulers
    -0.77
     unsupervised
    -0.75
    icamente
    -0.75
    unmodifiable
    -0.74
     đêm
    -0.73
    endy
    -0.73
    nesota
    -0.73
    ultati
    -0.73
    POSITIVE LOGITS
     skills
    3.02
     skill
    2.59
     Skills
    2.25
    skills
    2.22
    技能
    2.05
    Skills
    1.95
    skill
    1.95
     Skill
    1.92
     habilidades
    1.88
     abilities
    1.81
    Activations Density 0.009%

    No Known Activations