© 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. 26974
    Prev
    Next
    INDEX
    Explanations

    background information

    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
     always
    -1.16
     प्रोड
    -1.14
    änderung
    -1.08
    verkauf
    -1.05
     掃除
    -1.04
     سينما
    -1.00
    akang
    -0.99
     miljoen
    -0.98
     Ответить
    -0.96
    angolo
    -0.96
    POSITIVE LOGITS
    黜
    1.45
     السياس
    1.39
    maktadır
    1.24
     bendera
    1.23
    ּוֹ
    1.23
    脚步
    1.22
     mewah
    1.18
    Aho
    1.17
     merawat
    1.16
    ارک
    1.15
    Activations Density 0.002%

    No Known Activations