© 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. 55795
    Prev
    Next
    INDEX
    Explanations

    add or additionally

    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
    ленным
    -1.06
    だったが
    -1.05
    ::*;
    -1.04
    ιού
    -1.03
     much
    -1.03
     indeed
    -1.00
     dergleichen
    -1.00
     dù
    -0.99
    riturismo
    -0.97
     rather
    -0.97
    POSITIVE LOGITS
     zusätzlich
    2.27
    さらに
    2.13
     added
    2.08
     dodatk
    2.06
    还要
    2.06
     thêm
    2.00
    доба
    2.00
     navíc
    1.92
     ditambah
    1.90
     additionally
    1.84
    Activations Density 0.051%

    No Known Activations