© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20769
    Prev
    Next
    INDEX
    Explanations

    addresses, city, states

    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_16_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
    ě
    0.53
    6
    0.52
    adin
    0.51
    æk
    0.51
    åd
    0.51
    ajada
    0.50
    udahan
    0.50
    A
    0.50
    ressione
    0.49
    k
    0.49
    POSITIVE LOGITS
     কিন্ত
    0.55
     gxh
    0.55
    nahi
    0.53
     manoe
    0.52
    },\
    0.52
     pued
    0.51
    ים
    0.51
     autocorrelation
    0.51
     ～
    0.51
    䂙
    0.51
    Activations Density 0.003%

    No Known Activations