© 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. 31660
    Prev
    Next
    INDEX
    Explanations

    acquiring and developing skills

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

    The neuron selectively responds to words denoting actions of learning, training, or improving skills and knowledge.

    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
     kaynağından
    -0.95
     onPostExecute
    -0.84
    teras
    -0.84
    startActivity
    -0.82
    ģ
    -0.82
    opatho
    -0.81
     ImportError
    -0.79
    MatInputModule
    -0.78
    cessite
    -0.78
    IFF
    -0.78
    POSITIVE LOGITS
     skills
    5.13
    skills
    3.53
     skill
    3.50
     Skills
    2.86
    Skills
    2.81
     SKILLS
    2.61
    技能
    2.61
     habilidades
    2.45
    スキル
    2.34
    skill
    2.31
    Activations Density 0.060%

    No Known Activations