© 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. 248474
    Prev
    Next
    INDEX
    Explanations

    abandonment

    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
    ייש
    0.49
    ânico
    0.47
    뉘
    0.47
    inephrine
    0.46
    луу
    0.45
    ния
    0.44
    кот
    0.44
    뗑
    0.44
    ედ
    0.44
    лы
    0.43
    POSITIVE LOGITS
     abandonment
    0.50
     হঠাৎ
    0.49
     cuda
    0.48
     দ
    0.48
     Mati
    0.47
     abandon
    0.46
     abandoned
    0.46
     ragazza
    0.45
     voj
    0.45
     algebras
    0.45
    Activations Density 0.000%

    No Known Activations