© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1693
    Prev
    Next
    INDEX
    Explanations

    code blocks and comments

    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_262k_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
    𒐪
    0.70
     excellence
    0.65
     than
    0.63
     benevolent
    0.63
     neoliberal
    0.63
     realista
    0.62
     extravaganza
    0.62
     assimilation
    0.62
    .​
    0.61
     elucid
    0.61
    POSITIVE LOGITS
    ↵
    1.16
     /*
    0.89
    ↵↵
    0.85
    <0x0D>
    0.79
     /**
    0.79
     }
    0.78
     //}
    0.76
    /*
    0.74
    Если
    0.74
    Якщо
    0.74
    Activations Density 0.161%

    No Known Activations