© 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. 34-GEMMASCOPE-RES-131K
    7. 93262
    Prev
    Next
    INDEX
    Explanations

    code assignment and values

    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
    も
    -1.41
     作り方
    -1.34
    Also
    -1.34
     egenskaper
    -1.26
     annons
    -1.25
     epitome
    -1.25
     """",
    -1.24
    痙
    -1.23
     становника
    -1.22
     virke
    -1.21
    POSITIVE LOGITS
     prachtige
    1.16
    2
    1.16
    ようになりました
    1.16
     längere
    1.13
    了不少
    1.09
    了些
    1.09
     poign
    1.08
     وزار
    1.08
    了什么
    1.06
     eenvou
    1.05
    Activations Density 0.030%

    No Known Activations