© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34780
    Prev
    Next
    INDEX
    Explanations

    states of being; knowledge, ignorance

    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
     Although
    -1.19
     of
    -1.14
     during
    -1.09
    dacia
    -1.05
     ebenfalls
    -1.05
     There
    -1.03
     although
    -1.02
    Denne
    -1.02
     which
    -0.98
     so
    -0.96
    POSITIVE LOGITS
    TUAL
    1.20
    (;;)
    1.12
    ---|
    1.09
    isic
    1.04
     francès
    1.02
     anglès
    1.01
    trale
    1.01
    ntax
    1.01
    _-_
    1.00
     barato
    0.99
    Activations Density 0.011%

    No Known Activations