© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11693
    Prev
    Next
    INDEX
    Explanations

    org/ website paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    :'#
    1.17
     Yo
    1.16
    वेत
    1.15
    tracking
    1.14
     Ис
    1.12
    TIMEOUT
    1.11
     MÉ
    1.11
     Toxicology
    1.09
     Backend
    1.09
     BPA
    1.08
    POSITIVE LOGITS
     obliquely
    0.96
    窣
    0.85
     peripher
    0.82
    টি
    0.82
     ممکن
    0.81
    ক্ষিপ্ত
    0.80
     westward
    0.80
    żs
    0.79
    ubicin
    0.78
     পিতা
    0.78
    Activations Density 0.037%

    No Known Activations