© 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. 64858
    Prev
    Next
    INDEX
    Explanations

    checking variable types

    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
     utilisent
    -1.21
     voient
    -1.20
     utilisant
    -1.19
    赑
    -1.18
    剥が
    -1.16
     própri
    -1.14
    鸶
    -1.14
    runners
    -1.09
     adesivo
    -1.09
     noirs
    -1.09
    POSITIVE LOGITS
     it
    1.66
     this
    1.50
     what
    1.35
     or
    1.17
     your
    1.16
     people
    1.16
    However
    1.14
    There
    1.09
     There
    1.08
    It
    1.05
    Activations Density 0.003%

    No Known Activations