© 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. 25663
    Prev
    Next
    INDEX
    Explanations

    `androidx` and `AppCompat` Android libraries

    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
     its
    -1.48
     any
    -1.43
     to
    -1.41
     our
    -1.39
     for
    -1.37
     if
    -1.35
     from
    -1.30
     over
    -1.26
     their
    -1.23
     some
    -1.22
    POSITIVE LOGITS
     Dinas
    1.23
     encaje
    1.23
     WHOLE
    1.18
     despues
    1.18
     NINE
    1.17
     området
    1.16
     dilapidated
    1.16
    不仅仅
    1.16
     PERFECT
    1.15
     CORRECT
    1.15
    Activations Density 0.000%

    No Known Activations