© 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. 13196
    Prev
    Next
    INDEX
    Explanations

    . programmatic file paths

    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
     finds
    -1.09
     action
    -1.07
     women
    -1.05
    で
    -1.03
     project
    -1.03
    ge
    -1.02
     transport
    -1.02
     research
    -1.02
     content
    -1.00
     durante
    -0.98
    POSITIVE LOGITS
    jelaskan
    1.34
     berbasis
    1.31
    jedno
    1.21
     setempat
    1.19
     casó
    1.17
    Angebot
    1.16
    鑷
    1.16
     čia
    1.16
    Ciri
    1.11
     използ
    1.10
    Activations Density 0.083%

    No Known Activations