© 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. 10-GEMMASCOPE-RES-131K
    7. 113039
    Prev
    Next
    INDEX
    Explanations

    elongated

    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_10/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
    e
    -3.05
    崀
    -2.56
    y
    -2.53
     sogni
    -2.45
    ties
    -2.41
    越高
    -2.38
    r
    -2.30
    ATION
    -2.20
     een
    -2.19
     atau
    -2.17
    POSITIVE LOGITS
    臈
    2.44
    ly
    2.30
     französische
    2.27
    』、
    2.22
     skit
    2.17
    ｇ
    2.16
    ৄ
    2.16
    我在
    2.16
     ridd
    2.13
    鹟
    2.13
    Activations Density 0.036%

    No Known Activations