© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54535
    Prev
    Next
    INDEX
    Explanations

    Eureka! Tent Company

    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
     of
    -1.42
     garner
    -1.30
     epitom
    -1.23
     after
    -1.14
     Transporte
    -1.10
     revital
    -1.09
     Despite
    -1.06
     rejuven
    -1.06
     became
    -1.06
     After
    -1.06
    POSITIVE LOGITS
     ludicrous
    1.38
     ridiculously
    1.37
     MAKING
    1.35
     insanely
    1.31
    に行って
    1.30
     unbelievably
    1.29
     amazingly
    1.25
     remarkably
    1.20
     ridiculous
    1.20
     получают
    1.18
    Activations Density 0.000%

    No Known Activations