© 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. 73779
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    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
     on
    -1.63
     in
    -1.56
     by
    -1.27
     after
    -1.23
     will
    -1.18
     through
    -1.17
     from
    -1.16
     to
    -1.14
     octubre
    -1.10
    靄
    -1.10
    POSITIVE LOGITS
     another
    1.55
    another
    1.30
     molti
    1.27
    还有
    1.23
    อีก
    1.20
     exceptional
    1.18
     spectacular
    1.15
     thre
    1.15
     ANOTHER
    1.13
    3
    1.13
    Activations Density 0.004%

    No Known Activations