© 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. 7067
    Prev
    Next
    INDEX
    Explanations

    mathematical simplifications and code

    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
     too
    -0.88
     manipulations
    -0.81
     Are
    -0.78
     whether
    -0.75
     gì
    -0.74
     Geschäfts
    -0.73
     able
    -0.73
     manipulated
    -0.72
     triệu
    -0.72
    )}-
    -0.72
    POSITIVE LOGITS
     [])
    1.02
     ${(
    0.90
     recog
    0.86
     hardness
    0.86
    pherals
    0.85
     TRES
    0.84
    oquia
    0.84
     '*'
    0.83
     suf
    0.80
     KEV
    0.80
    Activations Density 0.046%

    No Known Activations