© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54237
    Prev
    Next
    INDEX
    Explanations

    now followed by action

    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
     later
    -1.32
     recently
    -1.30
     yet
    -1.23
     recent
    -1.22
    目前
    -1.15
     soon
    -1.11
    currentColor
    -1.10
     currently
    -1.09
     leeftijd
    -1.06
     sudah
    -1.05
    POSITIVE LOGITS
     sogar
    1.10
    B
    1.08
    Instead
    1.08
    co
    1.07
    can
    1.07
    y
    1.05
     nawet
    1.05
    H
    1.05
     jopa
    1.04
    z
    1.04
    Activations Density 0.070%

    No Known Activations