© 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. 54019
    Prev
    Next
    INDEX
    Explanations

    gain in

    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
    を行い
    -1.34
     rése
    -1.19
     rajut
    -1.16
    えっ
    -1.13
    イイ
    -1.13
    Ahol
    -1.10
    武田
    -1.10
     novin
    -1.09
     sonre
    -1.09
     asegur
    -1.09
    POSITIVE LOGITS
     again
    1.80
     did
    1.24
     with
    1.19
     for
    1.15
     опять
    1.13
    ogues
    1.11
     by
    1.05
     on
    1.03
     from
    1.02
    again
    1.02
    Activations Density 0.022%

    No Known Activations