© 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. 93184
    Prev
    Next
    INDEX
    Explanations

    further additional subsequent

    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
     akurat
    -0.96
    umeur
    -0.90
     incele
    -0.90
    הם
    -0.86
    ZED
    -0.86
     konstant
    -0.85
     Jenis
    -0.84
    ：@
    -0.84
     đổi
    -0.82
    fällig
    -0.82
    POSITIVE LOGITS
     further
    1.69
     additional
    1.68
     subsequent
    1.67
     other
    1.60
     thereafter
    1.57
     weitere
    1.55
     weiteren
    1.41
    additional
    1.38
     dalších
    1.34
     kolejne
    1.33
    Activations Density 0.068%

    No Known Activations