© 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. 67540
    Prev
    Next
    INDEX
    Explanations

    proper noun followed by a phrase

    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
     they
    -1.88
     it
    -1.52
     you
    -1.38
     will
    -1.34
     them
    -1.25
     and
    -1.22
    になるので
    -1.22
    cfr
    -1.18
     could
    -1.17
     głównie
    -1.16
    POSITIVE LOGITS
     two
    1.53
     a
    1.48
     another
    1.30
     peculiarly
    1.18
    getUserName
    1.16
     étage
    1.15
    прочем
    1.15
     два
    1.15
     recém
    1.14
     znajdu
    1.13
    Activations Density 0.099%

    No Known Activations