© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15286
    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
    Every
    -1.52
    Quite
    -1.45
     every
    -1.43
    Каждый
    -1.38
    Taking
    -1.38
    すべての
    -1.38
     作り方
    -1.37
    Unlike
    -1.37
    Having
    -1.36
    そして
    -1.35
    POSITIVE LOGITS
     pesada
    1.53
     plumme
    1.46
     insanely
    1.34
     delicada
    1.34
     manteniendo
    1.32
     frequentemente
    1.32
     ridiculously
    1.29
     exceptionally
    1.28
     gänzlich
    1.27
     zugänglich
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.