© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72745
    Prev
    Next
    INDEX
    Explanations

    when describing temporal conditions

    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
    ’).
    -1.19
    ᄆ
    -1.15
    ského
    -1.14
    producción
    -1.13
    cabulary
    -1.11
    』、
    -1.08
    куртка
    -1.07
     zweier
    -1.07
    hiti
    -1.07
    |}{
    -1.07
    POSITIVE LOGITS
     there
    1.56
    after
    1.34
     where
    1.34
     everything
    1.34
     we
    1.32
     it
    1.27
     they
    1.24
     everyone
    1.23
    Crítica
    1.20
    Where
    1.20
    Activations Density 0.018%

    No Known Activations