© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76449
    Prev
    Next
    INDEX
    Explanations

    language shapes reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     la
    0.55
    ي
    0.53
     Royal
    0.47
     royal
    0.47
    لا
    0.46
    Comedy
    0.46
    ค
    0.45
    ك
    0.44
    א
    0.44
    曛
    0.44
    POSITIVE LOGITS
    hosted
    0.48
    absorbing
    0.46
    fought
    0.45
    pertensive
    0.45
     সিস্টেম
    0.44
    activate
    0.44
    developed
    0.44
    stimulating
    0.43
     koristiti
    0.42
     سسٹم
    0.42
    Activations Density 0.012%

    No Known Activations