© 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. 65625
    Prev
    Next
    INDEX
    Explanations

    sharing posts or links

    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
    URSS
    -0.94
    saco
    -0.92
    магази
    -0.90
     Здесь
    -0.89
    针对
    -0.87
    JEN
    -0.85
     tinham
    -0.85
    ᄌ
    -0.84
     reparto
    -0.83
     توضی
    -0.83
    POSITIVE LOGITS
     on
    1.37
     your
    1.27
     via
    1.19
     to
    1.09
     with
    0.97
     friends
    0.93
     tweet
    0.90
     Tweet
    0.88
     rate
    0.86
     znaj
    0.84
    Activations Density 0.051%

    No Known Activations