© 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. 66657
    Prev
    Next
    INDEX
    Explanations

    subjective judgment and evaluation

    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
    łaszcza
    -1.05
    鳍
    -1.02
     المر
    -1.02
    Ephesians
    -0.97
     ausdrücklich
    -0.96
     diputados
    -0.93
     tytu
    -0.93
     arra
    -0.92
    胯
    -0.92
    ikat
    -0.92
    POSITIVE LOGITS
     decisions
    1.31
     based
    1.24
     judgement
    1.23
     judgment
    1.23
     subjective
    1.19
     judgments
    1.16
     decision
    1.16
     judgements
    1.13
    判斷
    1.07
    判断
    1.05
    Activations Density 0.123%

    No Known Activations