© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11932
    Prev
    Next
    INDEX
    Explanations

    initial states and beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     మొత్త
    0.48
    娯
    0.46
    များနှင့်
    0.43
    昴
    0.43
     হাস্য
    0.43
     daarmee
    0.42
     logros
    0.42
     მშ
    0.42
     lucro
    0.41
     immobilier
    0.40
    POSITIVE LOGITS
     imperfect
    0.50
     initial
    0.47
     differs
    0.43
     প্রথমে
    0.42
     initially
    0.42
    нача
    0.41
    ỳ
    0.40
    知道
    0.40
     inital
    0.40
    有两种
    0.39
    Activations Density 0.008%

    No Known Activations