© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103289
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     said
    -0.90
    をしました
    -0.90
     От
    -0.90
    красный
    -0.88
    柄
    -0.85
    The
    -0.85
    унд
    -0.84
    <<"
    -0.84
    出来た
    -0.82
    矛盾
    -0.81
    POSITIVE LOGITS
     \\
    1.55
    ↵↵↵
    1.07
    }\\
    1.05
     \\
    1.03
     />
    0.98
    ↵↵↵↵
    0.96
    ἴ
    0.96
    ↵↵↵↵↵
    0.96
    差别
    0.94
    獷
    0.94
    Activations Density 0.007%

    No Known Activations