© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27053
    Prev
    Next
    INDEX
    Explanations

    caret followed by symbol or version

    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
    akterysty
    -2.27
    珖
    -2.19
    浥
    -2.03
    ࿆
    -2.00
     populer
    -2.00
     about
    -1.98
    ）-
    -1.95
     endet
    -1.95
    特長
    -1.94
    
    -1.94
    POSITIVE LOGITS
    ’
    2.61
     faſt
    2.45
     impromptu
    2.09
     disgraceful
    2.08
    がっ
    2.06
    TemporalType
    2.05
     Hinblick
    2.05
     horrend
    2.05
    DebuggerNonUser
    2.02
     geschützt
    1.99
    Activations Density 0.022%

    No Known Activations