© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59374
    Prev
    Next
    INDEX
    Explanations

    adjusting, controlling, and tailoring

    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_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
    leyin
    -0.96
    addAll
    -0.87
    ṓ
    -0.86
     lösen
    -0.83
    kym
    -0.79
     remplace
    -0.78
    ⍝
    -0.77
    ツイ
    -0.77
    ="">
    -0.77
    мето
    -0.76
    POSITIVE LOGITS
     adjust
    3.81
     adjusting
    3.41
     control
    3.33
    adjust
    3.33
    Adjust
    3.30
     adjustment
    3.16
     Adjust
    3.08
     adjustable
    3.00
    調整
    2.98
     adjusts
    2.98
    Activations Density 0.335%

    No Known Activations