© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    conjunctions introducing conclusions

    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
    itaji
    -1.43
     décider
    -1.30
     démission
    -1.29
    ごめん
    -1.23
     Estructura
    -1.17
    raeli
    -1.16
    殽
    -1.16
    おそ
    -1.16
    vernote
    -1.16
     accompagné
    -1.14
    POSITIVE LOGITS
     all
    1.86
     in
    1.76
     by
    1.54
     there
    1.53
     both
    1.51
     is
    1.47
     even
    1.44
     after
    1.38
     only
    1.37
     every
    1.35
    Activations Density 0.009%

    No Known Activations