© 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. 3459
    Prev
    Next
    INDEX
    Explanations

    words followed by specific continuations

    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
     MLE
    0.84
     À
    0.84
     atas
    0.82
     diligent
    0.81
     vadanti
    0.81
    regional
    0.79
     manner
    0.79
    гласно
    0.79
     diploid
    0.78
     évalu
    0.77
    POSITIVE LOGITS
    あれ
    0.87
     још
    0.85
    ␊
    0.81
    ון
    0.78
    লাপ
    0.78
    AndPassword
    0.76
    갚
    0.76
    Ꮴ
    0.75
    ੭
    0.74
    ？）
    0.72
    Activations Density 0.098%

    No Known Activations