© 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. 34-GEMMASCOPE-RES-131K
    4. 60883
    Prev
    Next
    INDEX
    Explanations

    [word] of

    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_34/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
     Menschheit
    -1.23
    啲
    -1.09
     aislada
    -1.08
     rebajas
    -1.08
     táctil
    -1.08
     gruesa
    -1.07
     afectada
    -1.05
     acoged
    -1.05
     первом
    -1.04
    غا
    -1.02
    POSITIVE LOGITS
     of
    10.13
    ของ
    3.55
    of
    3.55
     Of
    3.38
     của
    3.20
    Of
    2.89
     של
    2.63
    OfType
    2.44
     OF
    2.39
    もちろん
    2.00
    Activations Density 0.312%

    No Known Activations