© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113593
    Prev
    Next
    INDEX
    Explanations

    sharing or posting content

    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
     The
    -1.64
     
    -1.38
    𝟑
    -1.34
    などなど
    -1.25
     почти
    -1.23
     originalen
    -1.21
     neuen
    -1.18
    tably
    -1.15
     कई
    -1.15
     akin
    -1.14
    POSITIVE LOGITS
     which
    1.78
     dager
    1.61
     lørdag
    1.59
     søndag
    1.55
    <bos>
    1.45
     montrer
    1.45
     imagenes
    1.41
    就可以
    1.41
     bø
    1.38
     kveld
    1.38
    Activations Density 0.105%

    No Known Activations