© 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. 22-GEMMASCOPE-RES-131K
    7. 39255
    Prev
    Next
    INDEX
    Explanations

    scientific citations and references

    np_acts-logits-general · gemini-2.5-flash-lite

    special syntax characters and notation in technical code or mathematical expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     tử
    -0.98
     着
    -0.97
     TÉCNICA
    -0.93
    .”
    -0.93
     Teilnehmer
    -0.90
     willst
    -0.90
    </strong>
    -0.88
    atleta
    -0.86
     mówi
    -0.86
    tribune
    -0.86
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.96
     Polonia
    0.95
    饜
    0.92
     réunions
    0.91
     ciudadana
    0.91
     flèche
    0.90
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.90
     tộc
    0.88
    Algo
    0.88
     exhort
    0.88
    Activations Density 0.014%

    No Known Activations