© 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. 36268
    Prev
    Next
    INDEX
    Explanations

    cause and effect of events

    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
    tiéndose
    -1.10
    quisar
    -1.09
    ]].
    -1.03
     firebaseConfig
    -1.01
    éraires
    -0.97
    ]};
    -0.96
    معلومات
    -0.96
    rég
    -0.95
     în
    -0.93
    معرفی
    -0.93
    POSITIVE LOGITS
     events
    1.38
     laws
    1.36
     we
    1.34
     our
    1.26
     observed
    1.23
     every
    1.20
     actions
    1.16
    æa
    1.16
    んだから
    1.13
     random
    1.13
    Activations Density 0.042%

    No Known Activations