© 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. 28394
    Prev
    Next
    INDEX
    Explanations

    through the use

    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
    who
    -1.17
    when
    -1.16
    など
    -1.10
     when
    -1.10
     how
    -1.09
     offer
    -1.09
     r
    -1.08
    や
    -1.07
     place
    -1.05
     quando
    -1.05
    POSITIVE LOGITS
     itali
    1.26
     algod
    1.25
     hırka
    1.21
     pamamagitan
    1.21
     semelh
    1.20
    ᐠ
    1.19
    咘
    1.15
     embre
    1.14
     inaugura
    1.13
    aktivi
    1.09
    Activations Density 0.065%

    No Known Activations