© 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. 107832
    Prev
    Next
    INDEX
    Explanations

    include specific details

    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
     TREAS
    -0.99
    ANZE
    -0.90
    Informa
    -0.88
     recapit
    -0.84
     marron
    -0.84
     озна
    -0.83
     Recap
    -0.83
    めに
    -0.82
     Indes
    -0.80
     PROCED
    -0.79
    POSITIVE LOGITS
     include
    1.73
     your
    1.53
    Include
    1.48
     Include
    1.38
     including
    1.38
    包括
    1.36
    具体
    1.33
    至少
    1.30
    include
    1.25
     incluyen
    1.23
    Activations Density 0.031%

    No Known Activations