© 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. 128575
    Prev
    Next
    INDEX
    Explanations

    foundations and grants

    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
     from
    -0.98
    ()}>
    -0.97
     sostu
    -0.96
    Поздрав
    -0.93
     oficiales
    -0.92
     atractivo
    -0.92
    uksi
    -0.90
     we
    -0.90
     provocó
    -0.89
     udang
    -0.89
    POSITIVE LOGITS
     funding
    1.56
     funds
    1.48
     funded
    1.20
     sponsoring
    1.13
    funded
    1.05
    evos
    1.03
     دعم
    1.03
     grants
    1.01
     grant
    1.01
     fund
    1.00
    Activations Density 0.042%

    No Known Activations