© 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. 66342
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     you
    -1.98
     for
    -1.52
     their
    -1.35
     your
    -1.32
     know
    -1.28
     will
    -1.26
     has
    -1.25
     have
    -1.21
     all
    -1.18
     who
    -1.13
    POSITIVE LOGITS
     erneu
    1.26
     fühlte
    1.20
     relacionada
    1.20
     vän
    1.14
    entieth
    1.13
    ₜ
    1.13
    Anche
    1.10
     глаза
    1.09
     costumbres
    1.09
     getragen
    1.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.