© 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. 10-GEMMASCOPE-RES-131K
    4. 105493
    Prev
    Next
    INDEX
    Explanations

    years and citations

    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
    èces
    -1.47
     einzelne
    -1.45
    al
    -1.40
    =>$
    -1.38
     emot
    -1.33
    $
    -1.32
    ון
    -1.31
    ଆ
    -1.30
     Amps
    -1.30
    служба
    -1.30
    POSITIVE LOGITS
    ↵
    1.72
    鍇
    1.59
    such
    1.51
     pracy
    1.46
     jed
    1.44
     buque
    1.42
    3
    1.39
     zelf
    1.38
    زندگی
    1.38
    ]
    1.37
    Activations Density 0.067%

    No Known Activations