© 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. 73623
    Prev
    Next
    INDEX
    Explanations

    organizations and applications

    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
    虬
    -1.24
    ריכה
    -1.23
    べし
    -1.19
    茬
    -1.19
     nedeniyle
    -1.18
    幾天
    -1.17
    頂いた
    -1.17
    ーーー
    -1.16
    ":"+
    -1.16
     COMPLE
    -1.15
    POSITIVE LOGITS
     any
    1.54
     only
    1.45
    下
    1.30
     nėra
    1.30
     their
    1.27
    随着
    1.16
    𝓖
    1.16
     some
    1.16
     کردن
    1.14
     my
    1.12
    Activations Density 0.503%

    No Known Activations