© 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. 221781
    Prev
    Next
    INDEX
    Explanations

    places and accounts

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

    describing appearance

    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
     p
    0.48
    eri
    0.47
     solen
    0.46
     l
    0.44
     c
    0.44
     curious
    0.42
     mardi
    0.42
     k
    0.41
     lupus
    0.41
    رو
    0.41
    POSITIVE LOGITS
     счет
    0.55
     рынке
    0.53
    Yeni
    0.52
    Uy
    0.52
    cuenta
    0.49
     счёт
    0.49
     שלו
    0.48
     Счет
    0.48
     θέση
    0.48
    িয়েছেন
    0.48
    Activations Density 0.000%

    No Known Activations