© 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. 104684
    Prev
    Next
    INDEX
    Explanations

    company website terms

    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
    ösen
    -1.18
    надца
    -1.13
    daki
    -1.12
    üre
    -1.11
    dö
    -1.10
     fritas
    -1.09
    ถ้า
    -1.07
     strutture
    -1.05
    ztes
    -1.05
    lında
    -1.05
    POSITIVE LOGITS
     your
    1.40
    にかく
    1.34
    your
    1.13
    ないし
    1.13
    三個
    1.13
     PLAINTIFF
    1.08
     взрос
    1.05
     you
    1.05
    おき
    1.05
    会的
    1.04
    Activations Density 0.033%

    No Known Activations