© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14838
    Prev
    Next
    INDEX
    Explanations

    specific nouns and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     implied
    0.97
     stated
    0.95
     acknowledged
    0.92
    ﻤ
    0.90
     signifies
    0.89
     radiates
    0.86
     described
    0.86
     fulfills
    0.86
     opposed
    0.86
     protr
    0.85
    POSITIVE LOGITS
    ת
    1.27
    isati
    1.22
     Scouts
    1.18
     scouts
    1.16
    ंछ
    1.15
    ০
    1.09
    idamente
    1.08
     nego
    1.05
    ្នុង
    1.03
    entliche
    1.02
    Activations Density 0.009%

    No Known Activations