© 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. 65074
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and algebra

    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
    ologues
    -1.06
    ruzzo
    -1.06
    ázaro
    -1.02
     таких
    -0.98
     solchen
    -0.96
    oved
    -0.93
    Excluir
    -0.93
     takich
    -0.92
    empêcher
    -0.90
     inversión
    -0.90
    POSITIVE LOGITS
     and
    1.02
    ២
    0.94
     procéder
    0.94
    ”，
    0.92
     roberto
    0.88
     between
    0.88
     گرفتن
    0.86
     sevilla
    0.84
    無く
    0.84
     iyong
    0.82
    Activations Density 0.006%

    No Known Activations