© 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. 104400
    Prev
    Next
    INDEX
    Explanations

    promoting or leading to outcomes

    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
     poème
    -1.05
    //*/
    -1.00
     ночи
    -0.99
     ovate
    -0.97
     BERNAMA
    -0.94
    すでに
    -0.93
     herbes
    -0.93
     belum
    -0.93
     to
    -0.93
    既に
    -0.90
    POSITIVE LOGITS
     more
    1.31
     जाता
    1.23
     better
    1.23
    ulemon
    1.16
    ншот
    1.15
    }],
    1.15
     necessary
    1.14
     greater
    1.12
    了一眼
    1.12
    ACIONES
    1.10
    Activations Density 0.028%

    No Known Activations