© 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. 115264
    Prev
    Next
    INDEX
    Explanations

    updates on

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

    AIDA, Carta, Cloud, waves

    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
    ক
    0.54
    kke
    0.49
    গম
    0.46
     lalu
    0.46
     然后
    0.46
    кә
    0.45
     йөк
    0.45
     då
    0.44
     majd
    0.44
    ｂ
    0.44
    POSITIVE LOGITS
     puterea
    0.48
     reformed
    0.46
    3
    0.46
     revelation
    0.45
     pervasive
    0.45
     न्यूमेरिकल
    0.45
    സ്ഥാന
    0.44
    统治
    0.44
     are
    0.43
    ുപത്രി
    0.43
    Activations Density 0.001%

    No Known Activations