© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10136
    Prev
    Next
    INDEX
    Explanations

    listing groups

    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_22_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
    そして
    0.93
     그리고
    0.92
    swith
    0.83
     そして
    0.81
    ጠ
    0.79
     entrenched
    0.79
     breached
    0.78
    ავს
    0.77
     پیشہ
    0.77
    ivable
    0.77
    POSITIVE LOGITS
    ˨
    0.84
    ুটি
    0.80
     ভিট
    0.76
    ᗰ
    0.75
    ছিল
    0.74
     unofficial
    0.72
     төр
    0.72
    žd
    0.71
    нициа
    0.71
    elsk
    0.70
    Activations Density 0.003%

    No Known Activations