© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125299
    Prev
    Next
    INDEX
    Explanations

    poached egg pan

    np_acts-logits-general · gemini-2.5-flash-lite

    serif, Roman, Framework, mei

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    0.56
     ville
    0.50
     dav
    0.46
     with
    0.44
    ด้าน
    0.44
     entfernt
    0.43
     '>'
    0.43
     dư
    0.42
     প্রতিনি
    0.42
     weg
    0.42
    POSITIVE LOGITS
     आग्रह
    0.49
     evrops
    0.47
    quela
    0.46
    markUp
    0.46
     Ainda
    0.46
    criar
    0.45
    Todas
    0.44
    ும்பி
    0.44
    માં
    0.44
    安慰
    0.44
    Activations Density 0.000%

    No Known Activations