© 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. 16213
    Prev
    Next
    INDEX
    Explanations

    variable assignments

    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
     logos
    0.80
    u
    0.79
    いや
    0.77
    vocab
    0.75
     genere
    0.74
     Auft
    0.74
     presenti
    0.74
    นำ
    0.73
    جھ
    0.72
     infos
    0.72
    POSITIVE LOGITS
    ń
    1.09
    ştir
    1.00
    localVarPath
    0.99
    iren
    0.98
    aing
    0.96
    ıldığı
    0.95
    ordano
    0.95
     mapStateToProps
    0.94
    ಲ್ಲಿ
    0.94
    indak
    0.93
    Activations Density 0.179%

    No Known Activations