© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130656
    Prev
    Next
    INDEX
    Explanations

    specific multi-word terms

    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
     these
    -1.06
    S
    -1.05
     also
    -1.04
     those
    -0.94
    P
    -0.90
     éstos
    -0.87
    DOD
    -0.87
     instantly
    -0.87
    To
    -0.86
     Unlike
    -0.86
    POSITIVE LOGITS
    を見つけ
    1.05
    Ostat
    1.03
    ꪻ
    1.01
    arrive
    1.00
     corrom
    0.98
    髯
    0.97
    gelopen
    0.97
     beſt
    0.95
    muñeca
    0.95
     خدمات
    0.94
    Activations Density 0.256%

    No Known Activations