© 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. 39970
    Prev
    Next
    INDEX
    Explanations

    company names and organizations

    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
    感は
    -1.21
     method
    -1.20
     time
    -1.16
    を行い
    -1.16
     available
    -1.07
     opportunity
    -1.06
    にい
    -1.04
     onset
    -1.02
     felt
    -1.01
     fhort
    -1.00
    POSITIVE LOGITS
    などが
    1.20
     Eſ
    1.18
    咂
    1.13
    heben
    1.13
     Atención
    1.13
    льники
    1.09
    最近は
    1.09
    sometimes
    1.08
     parfois
    1.08
     行っ
    1.06
    Activations Density 0.058%

    No Known Activations