© 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. 98179
    Prev
    Next
    INDEX
    Explanations

    Band followed by specific suffixes

    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
     deal
    -0.80
     Schwartz
    -0.71
    ≅
    -0.71
    فتح
    -0.71
    UnityEngine
    -0.70
     crear
    -0.70
     '>=
    -0.70
    ₎
    -0.70
    uresh
    -0.70
    воря
    -0.70
    POSITIVE LOGITS
    ären
    0.82
     SERIAL
    0.76
     McCon
    0.74
     Objetivos
    0.74
    Iv
    0.73
    NIS
    0.73
    んだり
    0.73
     dessinée
    0.73
     GOS
    0.72
    ază
    0.71
    Activations Density 0.016%

    No Known Activations