© 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. 10-GEMMASCOPE-RES-131K
    7. 113494
    Prev
    Next
    INDEX
    Explanations

    Paris agreement, universities, attacks

    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_10/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
    
    -2.47
    ⩴
    -2.30
    ↵↵
    -2.30
     unſ
    -2.28
    ейчас
    -2.25
    眥
    -2.22
     --
    -2.20
    睃
    -2.20
    不着
    -2.20
    昻
    -2.19
    POSITIVE LOGITS
    of
    3.47
     Such
    2.73
    逦
    2.59
    }$
    2.52
    e
    2.48
     Then
    2.25
    ization
    2.20
    縯
    2.16
     onze
    2.13
     These
    2.09
    Activations Density 0.004%

    No Known Activations