© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84236
    Prev
    Next
    INDEX
    Explanations

    quoted defined terms

    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
     Incluso
    -1.12
    ！』
    -1.04
    ……。
    -1.01
    achim
    -1.00
    никах
    -1.00
    などを
    -0.99
     kleinere
    -0.99
    izacao
    -0.97
     möchtest
    -0.96
    𝓘
    -0.96
    POSITIVE LOGITS
    决赛
    1.15
    几十
    1.09
    Menurutnya
    1.08
     negozio
    1.07
    大半
    1.06
    SITE
    1.05
     Gesund
    1.05
     cihaz
    1.02
     new
    0.99
    تمام
    0.97
    Activations Density 0.021%

    No Known Activations