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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11539
    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
     their
    -1.79
     these
    -1.58
     both
    -1.52
     any
    -1.52
     diferen
    -1.51
     persil
    -1.43
    hadapi
    -1.43
     turista
    -1.42
     several
    -1.42
     those
    -1.42
    POSITIVE LOGITS
    al
    1.38
    j
    1.34
    "
    1.33
    urther
    1.30
    ’
    1.26
    h
    1.25
     welchen
    1.25
     opulent
    1.23
    et
    1.23
    л
    1.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.