© 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. 10028
    Prev
    Next
    INDEX
    Explanations

    but and butt words

    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
     csak
    1.00
    こそ
    0.97
     علاوہ
    0.95
    𝘰
    0.93
    ουλ
    0.92
    𝕆
    0.88
    に加え
    0.87
    hiba
    0.87
    鏄
    0.87
    requenz
    0.86
    POSITIVE LOGITS
    ்
    0.87
    ়
    0.85
    אַ
    0.76
    おすすめです
    0.75
     once
    0.75
    ফতরের
    0.73
     isn
    0.73
               
    0.72
    it
    0.71
    Clicked
    0.70
    Activations Density 0.004%

    No Known Activations