© 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. 63230
    Prev
    Next
    INDEX
    Explanations

    certain types and conditions

    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
    และ
    -1.94
     différentes
    -1.62
     唯美
    -1.56
     différents
    -1.52
    鵙
    -1.48
    糁
    -1.41
     diferentes
    -1.40
    𓍊
    -1.37
     aussit
    -1.37
     puissent
    -1.36
    POSITIVE LOGITS
     types
    2.34
     certain
    2.19
     kinds
    2.16
     kind
    1.90
     specific
    1.77
    特定的
    1.70
     amount
    1.66
     specified
    1.63
     type
    1.59
    特定
    1.55
    Activations Density 0.069%

    No Known Activations