© 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. 23648
    Prev
    Next
    INDEX
    Explanations

    code comments and keywords

    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
     myself
    -0.92
    FIC
    -0.90
    IDEN
    -0.86
    眨
    -0.84
    SMT
    -0.84
    ˾
    -0.82
    ных
    -0.82
    KET
    -0.82
     muitos
    -0.81
    感兴趣
    -0.80
    POSITIVE LOGITS
     /*
    1.06
     which
    0.89
    /*
    0.89
     شاید
    0.88
    átil
    0.84
    taway
    0.83
    (/*
    0.83
    }/*
    0.81
    digheid
    0.81
     włos
    0.79
    Activations Density 0.005%

    No Known Activations