© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72070
    Prev
    Next
    INDEX
    Explanations

    future commitments or agreements

    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
     Depois
    -1.08
     Because
    -1.00
     still
    -0.98
     Despite
    -0.98
     After
    -0.97
     their
    -0.96
     Unlike
    -0.95
     Unfortunately
    -0.94
    种子
    -0.94
     Wikimédia
    -0.94
    POSITIVE LOGITS
    ↵↵
    1.06
     dando
    1.02
     lauded
    0.97
    Île
    0.97
    mathrm
    0.95
     volledige
    0.94
    和他
    0.94
     çeşit
    0.93
     revamped
    0.92
    跟他
    0.91
    Activations Density 0.041%

    No Known Activations