© 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. 84324
    Prev
    Next
    INDEX
    Explanations

    succeeding previous officeholders

    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
    小学
    -1.04
    colata
    -0.96
    大阪
    -0.94
    お願いします
    -0.93
     dovol
    -0.93
     septembrie
    -0.91
    Litteratur
    -0.90
    логические
    -0.89
    包含
    -0.89
     and
    -0.87
    POSITIVE LOGITS
     previous
    1.40
     who
    1.31
     предыду
    1.28
     anteriores
    1.15
     retiring
    1.14
     сказки
    1.12
     vorige
    1.10
     last
    1.09
     predecessors
    1.05
     hubo
    1.03
    Activations Density 0.047%

    No Known Activations