© 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. 10-GEMMASCOPE-RES-131K
    7. 123991
    Prev
    Next
    INDEX
    Explanations

    types and categories

    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_10/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
     same
    -1.43
     is
    -1.35
     selben
    -1.31
     همان
    -1.27
     largely
    -1.25
     are
    -1.25
    U
    -1.21
    actéristi
    -1.18
    他
    -1.16
     如
    -1.13
    POSITIVE LOGITS
     but
    1.69
     tierras
    1.42
    軼
    1.38
    ènements
    1.37
    Fotó
    1.31
     velocidades
    1.30
     heridas
    1.30
    噱
    1.28
     võib
    1.27
     virtudes
    1.27
    Activations Density 0.062%

    No Known Activations