© 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. 10-GEMMASCOPE-RES-131K
    7. 10309
    Prev
    Next
    INDEX
    Explanations

    version numbers and identifiers

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

    version numbers in technical documentation and code files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     the
    -3.02
    -
    -2.23
     '
    -1.87
     nossa
    -1.84
                    
    -1.84
     With
    -1.80
     reveals
    -1.80
     sechs
    -1.80
     Bestimm
    -1.73
     of
    -1.67
    POSITIVE LOGITS
     vectorstock
    2.45
    1
    2.30
    ’
    2.14
    棪
    2.11
    鼋
    2.11
    숑
    2.06
     parachoque
    2.05
     batal
    2.00
    ⢅
    1.99
     Futbol
    1.98
    Activations Density 0.039%

    No Known Activations