© 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. 60512
    Prev
    Next
    INDEX
    Explanations

    initiating explanation or action

    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
     kérd
    -1.48
     manualidades
    -1.41
     vizsg
    -1.40
     pegatina
    -1.36
     almohada
    -1.31
     możemy
    -1.30
     colgante
    -1.29
     Flasche
    -1.28
     használ
    -1.28
     baratas
    -1.27
    POSITIVE LOGITS
     to
    5.72
    to
    1.68
     atlik
    1.38
    though
    1.15
     To
    1.12
     too
    1.11
     तो
    1.10
     به
    1.05
     regal
    1.05
    🤙
    1.05
    Activations Density 0.063%

    No Known Activations