© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    Q: followed by phrase, Endocrine response, No sooner has

    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_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
     this
    -1.23
     There
    -1.15
     muualla
    -1.09
    curkan
    -1.06
    Because
    -1.00
    >')
    -1.00
    」，
    -0.97
    研究院
    -0.95
    具有
    -0.94
     COMERC
    -0.94
    POSITIVE LOGITS
    がありますが
    1.16
    では
    1.09
     oft
    1.07
     canh
    1.01
     somewhat
    1.00
    朋友圈
    1.00
     nô
    0.98
     núm
    0.98
    Agen
    0.97
    CENT
    0.97
    Activations Density 0.000%

    No Known Activations