© 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. 34-GEMMASCOPE-RES-131K
    7. 86994
    Prev
    Next
    INDEX
    Explanations

    names ending in di or i

    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_34/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
    hema
    -0.79
     Things
    -0.76
     Eth
    -0.73
     метал
    -0.71
    incidence
    -0.69
     misunder
    -0.69
    zung
    -0.69
    瀝
    -0.68
     things
    -0.68
    ramble
    -0.68
    POSITIVE LOGITS
    expectedResult
    0.84
     lande
    0.77
    Formato
    0.75
     reguli
    0.73
     boeken
    0.73
    ływ
    0.73
    timeStamp
    0.72
    Whether
    0.72
    Kode
    0.71
    Geografia
    0.71
    Activations Density 0.086%

    No Known Activations