© 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. 53124
    Prev
    Next
    INDEX
    Explanations

    survive, leave, finish

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

    leaving behind

    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
     باستخدام
    0.49
    사용
    0.48
     utilizzo
    0.48
     రోజు
    0.44
     utilizando
    0.43
     பயன்படுத்தி
    0.43
    嘮
    0.43
     utilisons
    0.42
     استخدم
    0.42
     snowfall
    0.41
    POSITIVE LOGITS
    留
    0.51
    留下
    0.48
     leave
    0.47
     leaving
    0.47
     oeuvre
    0.46
     spouse
    0.46
     heirs
    0.45
    wiek
    0.45
     Hana
    0.44
    ained
    0.44
    Activations Density 0.025%

    No Known Activations