© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70428
    Prev
    Next
    INDEX
    Explanations

    Solve equations and C++ code

    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
     pérd
    -1.96
     constater
    -1.87
     incrí
    -1.84
     zoude
    -1.72
     charmant
    -1.69
     jugos
    -1.68
     dezelve
    -1.68
     anún
    -1.67
     plafon
    -1.66
     serre
    -1.66
    POSITIVE LOGITS
     also
    2.08
     what
    1.63
     but
    1.59
     S
    1.52
     with
    1.51
     to
    1.48
     all
    1.44
     U
    1.44
     K
    1.43
     M
    1.40
    Activations Density 0.000%

    No Known Activations