© 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. 1423
    Prev
    Next
    INDEX
    Explanations

    what comes next

    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
    肄
    0.82
    堕
    0.81
     सरकारी
    0.81
    謖
    0.80
     powdered
    0.80
     scandals
    0.79
    [,,"
    0.78
    ွ
    0.78
     distinctive
    0.77
     dhinak
    0.77
    POSITIVE LOGITS
     nantinya
    0.92
    next
    0.88
     berikutnya
    0.82
    Next
    0.81
     next
    0.81
    APTER
    0.80
     later
    0.76
     prossima
    0.76
     nanti
    0.74
     Next
    0.71
    Activations Density 0.788%

    No Known Activations