© 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. 22-GEMMASCOPE-RES-131K
    4. 11074
    Prev
    Next
    INDEX
    Explanations

    specific legal warranty or database term

    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_22/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
     with
    -1.53
     During
    -1.23
     that
    -1.21
     With
    -1.21
     when
    -1.17
     while
    -1.16
     for
    -1.16
     from
    -1.11
     Several
    -1.09
     despite
    -1.08
    POSITIVE LOGITS
     nimmer
    1.44
    もあるので
    1.27
    を
    1.20
    があるので
    1.19
    9
    1.11
    wachsenen
    1.07
    从来
    1.05
     Dinas
    1.05
     SEVENTH
    1.04
    や
    1.04
    Activations Density 0.009%

    No Known Activations