© 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. 15148
    Prev
    Next
    INDEX
    Explanations

    property = value, pin to

    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
     that
    -1.36
     all
    -1.32
     this
    -1.32
     which
    -1.31
     whose
    -1.27
     any
    -1.24
     their
    -1.20
     susceptibles
    -1.19
     for
    -1.18
     berangkat
    -1.18
    POSITIVE LOGITS
     manna
    1.27
     gänzlich
    1.23
    Contras
    1.23
     mehrm
    1.22
     otter
    1.14
     problemlos
    1.13
     nochmals
    1.12
     delightfully
    1.12
    Descrizione
    1.11
     implor
    1.11
    Activations Density 0.000%

    No Known Activations