© 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. 10-GEMMASCOPE-RES-131K
    7. 84169
    Prev
    Next
    INDEX
    Explanations

    words starting with "sem"

    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_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
    ↵
    -4.34
     
    -3.55
     In
    -2.78
     Also
    -2.66
     Their
    -2.64
     The
    -2.63
    ти
    -2.59
     Another
    -2.56
     They
    -2.55
     About
    -2.55
    POSITIVE LOGITS
    珢
    3.78
    }$
    3.56
    鴆
    3.33
    焢
    2.75
    饜
    2.69
    utriche
    2.66
    ндарт
    2.64
    蓆
    2.63
    tifying
    2.61
    蚍
    2.59
    Activations Density 0.017%

    No Known Activations