© 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. 84179
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    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
    鲧
    -3.30
     monumentos
    -3.22
    涠
    -3.13
    ⩴
    -3.06
    ſſen
    -3.05
    gezogen
    -2.95
     директор
    -2.94
    ementara
    -2.94
     pauv
    -2.92
     chimie
    -2.91
    POSITIVE LOGITS
     Their
    4.06
     
    3.59
    ’
    3.58
    It
    3.39
     Typical
    3.14
     Then
    3.11
    This
    3.08
     They
    3.06
    In
    2.95
     Rather
    2.84
    Activations Density 0.292%

    No Known Activations