© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3477
    Prev
    Next
    INDEX
    Explanations

    block of code or reader

    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_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
     nations
    0.70
    രുടെയും
    0.68
     environ
    0.68
     최종
    0.68
     탐
    0.68
     accretion
    0.65
    ぞれ
    0.64
     inspections
    0.64
    doped
    0.64
    options
    0.63
    POSITIVE LOGITS
     tandis
    0.90
     texto
    0.85
     terwijl
    0.82
    Text
    0.81
    <unused164>
    0.79
     palavras
    0.78
     enquanto
    0.78
    㘟
    0.77
     чтобы
    0.77
     иначе
    0.76
    Activations Density 0.023%

    No Known Activations