© 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. 22-GEMMASCOPE-RES-131K
    7. 9304
    Prev
    Next
    INDEX
    Explanations

    parts of specific names

    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
     pisa
    -1.40
     ideen
    -1.40
     inova
    -1.40
     precin
    -1.35
     diagrama
    -1.35
     jaket
    -1.35
     mesin
    -1.35
     revisor
    -1.33
     mixta
    -1.32
     ralla
    -1.31
    POSITIVE LOGITS
     refirió
    1.20
    or
    1.16
    Passe
    1.13
     häufiger
    1.13
     voedsel
    1.13
     you
    1.11
    になる
    1.10
     '\''
    1.09
    Salva
    1.09
     estiver
    1.08
    Activations Density 0.000%

    No Known Activations