© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14592
    Prev
    Next
    INDEX
    Explanations

    csrf token, form creation

    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
    ᯾
    -1.21
     convite
    -1.16
     laman
    -1.15
     tdci
    -1.09
     aeroporto
    -1.09
     easily
    -1.09
     acidente
    -1.08
    👍🏻
    -1.08
    matthew
    -1.06
     ensaio
    -1.05
    POSITIVE LOGITS
    Ն
    1.17
    קס
    1.02
    Ե
    1.01
    öhe
    1.00
     насеља
    0.99
    diera
    0.97
    влению
    0.96
     включая
    0.96
    rophore
    0.95
     minimalistic
    0.94
    Activations Density 0.001%

    No Known Activations