© 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. 76544
    Prev
    Next
    INDEX
    Explanations

    questions, names, `CVS`, `Bootstrap`

    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
     Provence
    -0.85
     MPH
    -0.81
     danish
    -0.79
     Reyn
    -0.75
     Amir
    -0.75
    pples
    -0.75
    āci
    -0.75
    eley
    -0.73
     Maas
    -0.73
     drinkers
    -0.71
    POSITIVE LOGITS
     cms
    0.99
    cms
    0.88
    FSM
    0.88
     ço
    0.87
    StatusCode
    0.85
    ednesday
    0.79
     заяви
    0.79
     pè
    0.76
    iov
    0.74
     TeV
    0.74
    Activations Density 0.025%

    No Known Activations