© 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. 383
    Prev
    Next
    INDEX
    Explanations

    targeting specific audiences

    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
     when
    -1.25
    rounder
    -1.10
     each
    -1.09
     reports
    -1.09
     corred
    -1.08
     reputa
    -1.07
    henge
    -1.05
     reported
    -1.05
     items
    -1.05
     practice
    -1.03
    POSITIVE LOGITS
     audiences
    1.38
     lewat
    1.38
     audience
    1.35
     zainteres
    1.22
     THOSE
    1.16
     tých
    1.14
    了一眼
    1.13
     wiem
    1.12
     people
    1.10
     principalmente
    1.09
    Activations Density 0.047%

    No Known Activations