© 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. 49859
    Prev
    Next
    INDEX
    Explanations

    module loading and definitions

    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
     its
    -1.19
    6
    -1.05
    ....
    -1.00
     now
    -0.99
     many
    -0.98
    3
    -0.98
     weirdly
    -0.98
     surprisingly
    -0.98
     time
    -0.96
    ="
    -0.96
    POSITIVE LOGITS
     새로운
    1.20
    はもちろん
    1.06
    conos
    1.03
    jgl
    1.02
     vacunas
    1.00
    terapia
    1.00
    roasted
    0.98
    の方に
    0.98
     erhi
    0.98
    '},
    0.97
    Activations Density 0.005%

    No Known Activations