© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    introduces exceptions or further 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
    otho
    -1.49
     vó
    -1.44
     poté
    -1.40
     bezw
    -1.38
     cia
    -1.38
    ってきて
    -1.36
     TILL
    -1.35
     châ
    -1.34
    quiv
    -1.33
    '.'
    -1.32
    POSITIVE LOGITS
     often
    2.61
    Often
    2.53
     Often
    2.41
     for
    2.36
     many
    2.23
     such
    2.22
     where
    2.19
     in
    2.09
    Sometimes
    2.08
     sometimes
    2.06
    Activations Density 0.191%

    No Known Activations