© 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. 55572
    Prev
    Next
    INDEX
    Explanations

    as defined or specified

    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
     as
    -1.29
    śla
    -0.93
    Gratis
    -0.90
    为例
    -0.90
    SALUD
    -0.87
    Nevermind
    -0.86
    Testi
    -0.86
    tså
    -0.85
    Cual
    -0.85
    Можно
    -0.85
    POSITIVE LOGITS
     soon
    1.26
     discussed
    1.19
     to
    1.12
     between
    1.09
     follows
    1.09
     originally
    1.06
     part
    1.05
     described
    1.02
     explained
    1.01
     herein
    0.95
    Activations Density 0.043%

    No Known Activations