© 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. 38454
    Prev
    Next
    INDEX
    Explanations

    quantities and equivalences

    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
    ⁓
    -0.81
     pudesse
    -0.79
    Beloved
    -0.79
     bordada
    -0.75
    quero
    -0.75
     Länge
    -0.75
    словия
    -0.74
    ﾟ)
    -0.73
    وسط
    -0.73
     auténtica
    -0.73
    POSITIVE LOGITS
     equal
    4.59
     equivalent
    4.38
    equal
    3.56
    equivalent
    3.45
     commensurate
    3.28
     Equivalent
    3.00
     equivalente
    2.91
    Equal
    2.91
    Equivalent
    2.91
     Equal
    2.83
    Activations Density 0.155%

    No Known Activations