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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34326
    Prev
    Next
    INDEX
    Explanations

    progress and parallel execution

    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
    欵
    -1.30
    Bereits
    -1.21
     tačiau
    -1.21
     separately
    -1.14
     või
    -1.14
     acciaio
    -1.11
     strategy
    -1.08
    煕
    -1.07
     realizzare
    -1.06
     unmittelbar
    -1.05
    POSITIVE LOGITS
     tqdm
    1.12
    тисти
    1.09
    趄
    1.03
    liciter
    1.02
     artista
    0.99
    ensacola
    0.98
    スーツ
    0.96
    臉
    0.94
    ف
    0.94
     patients
    0.93
    Activations Density 0.001%

    No Known Activations