© 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. 34-GEMMASCOPE-RES-131K
    7. 81153
    Prev
    Next
    INDEX
    Explanations

    academic 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_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
    Metode
    -1.20
    Karakter
    -1.16
    بررسی
    -1.11
     sako
    -1.10
     शुर
    -1.03
     gastar
    -1.01
    lampada
    -1.00
    skyline
    -1.00
    Teknik
    -1.00
     شدند
    -0.99
    POSITIVE LOGITS
    av
    1.17
     contemp
    1.13
    on
    1.09
    am
    1.05
    ong
    1.05
    og
    1.05
    ru
    1.03
    oo
    1.02
    にも
    1.02
    ?"
    1.02
    Activations Density 0.159%

    No Known Activations