© 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. 70953
    Prev
    Next
    INDEX
    Explanations

    qualifications and exceptions

    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
     now
    -1.18
     already
    -1.05
     właśnie
    -0.94
     уже
    -0.94
     только
    -0.93
     only
    -0.90
    早就
    -0.88
    tät
    -0.87
    更
    -0.85
     need
    -0.84
    POSITIVE LOGITS
    sometimes
    1.44
    variables
    1.29
     parfois
    1.28
    factors
    1.27
    Sometimes
    1.20
     sometimes
    1.20
    mittedly
    1.17
    Unfortunately
    1.13
     manchmal
    1.12
     иногда
    1.11
    Activations Density 0.032%

    No Known Activations