© 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. 70999
    Prev
    Next
    INDEX
    Explanations

    empty list or nothing

    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
     of
    -0.94
    estens
    -0.89
    >>(
    -0.88
     inequ
    -0.85
     lugar
    -0.85
     Suède
    -0.85
    Hs
    -0.84
     (
    -0.84
    ulmuş
    -0.83
    筍
    -0.82
    POSITIVE LOGITS
     neither
    1.34
     nothing
    1.27
    Nothing
    1.19
    Neither
    1.17
     tampoco
    1.15
     empty
    1.14
     absence
    1.11
    ="";
    1.10
     vazio
    1.09
     nobody
    1.05
    Activations Density 0.015%

    No Known Activations