© 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. 13408
    Prev
    Next
    INDEX
    Explanations

    all or each

    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
     such
    -1.59
     even
    -1.34
     many
    -1.17
     такі
    -1.09
     takie
    -1.05
     two
    -1.05
     there
    -1.05
     only
    -1.02
     telles
    -1.00
     like
    -0.98
    POSITIVE LOGITS
     jeweils
    1.48
    それぞれ
    1.47
    Each
    1.45
    either
    1.44
    それぞれの
    1.42
     EACH
    1.36
    each
    1.33
    都有
    1.33
    Either
    1.28
    各自
    1.27
    Activations Density 0.071%

    No Known Activations