© 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. 26277
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific subjects

    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
     with
    -1.11
    Having
    -1.06
    Many
    -1.05
     superbly
    -1.03
     allows
    -1.02
    With
    -1.00
     ONLY
    -0.98
     only
    -0.96
    While
    -0.93
    During
    -0.93
    POSITIVE LOGITS
     HALF
    1.15
    originally
    1.02
     intriguing
    0.96
     captivating
    0.96
    和他
    0.95
     ‏
    0.94
    tikel
    0.93
    enedig
    0.93
    truct
    0.93
    ound
    0.92
    Activations Density 0.086%

    No Known Activations