© 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. 28559
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
     TODO
    -1.09
     /
    -1.05
     More
    -1.04
     vollständige
    -1.01
     http
    -1.01
     et
    -0.98
     ``
    -0.98
     --
    -0.96
     In
    -0.96
     The
    -0.96
    POSITIVE LOGITS
    デニム
    1.12
    OOTDTY
    1.11
     tortas
    1.09
    drucks
    1.07
     nabi
    1.07
     decoracion
    1.05
     jouant
    1.04
    puerta
    1.02
    ついに
    1.02
     掛
    1.02
    Activations Density 0.043%

    No Known Activations