© 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. 77389
    Prev
    Next
    INDEX
    Explanations

    copyright, file, license, deal

    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
     карти
    -0.84
     suburbs
    -0.83
     piss
    -0.83
    恭喜
    -0.83
    Insight
    -0.82
    ClientSize
    -0.82
    STRUCT
    -0.79
     Literatur
    -0.79
     fairing
    -0.78
     Жу
    -0.77
    POSITIVE LOGITS
    文學
    0.82
    攤
    0.75
    ᥉
    0.73
    
    0.73
     απο
    0.72
     ور
    0.68
    应该
    0.67
     。
    0.66
    specifically
    0.66
     lod
    0.66
    Activations Density 0.221%

    No Known Activations