© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117461
    Prev
    Next
    INDEX
    Explanations

    numbers followed by million

    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
    uego
    -0.93
    ToPoint
    -0.91
     iArr
    -0.82
    XPATH
    -0.82
    ！");
    -0.80
    INOS
    -0.76
    ntos
    -0.75
    蛄
    -0.75
    пратки
    -0.75
    topRight
    -0.75
    POSITIVE LOGITS
     million
    1.08
    tasting
    0.84
     miał
    0.83
    secution
    0.82
     thousand
    0.81
     penjual
    0.77
    ulha
    0.76
    pim
    0.75
    retum
    0.75
    nil
    0.75
    Activations Density 0.014%

    No Known Activations