© 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. 34267
    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
     desfile
    -1.48
    Zubereitung
    -1.45
    に行ってきました
    -1.32
     Vergrößern
    -1.31
     чехол
    -1.30
    以及
    -1.29
     any
    -1.27
     its
    -1.24
    Что
    -1.22
     joyería
    -1.22
    POSITIVE LOGITS
     nimble
    1.15
    ica
    1.13
    ll
    1.09
    -
    1.09
     betreffende
    1.08
     tentunya
    1.07
     he
    1.06
     יְ
    1.05
    fdata
    1.05
    /*!
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.