© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1770
    Prev
    Next
    INDEX
    Explanations

    spacer, shavings, chips

    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_16_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
    한
    0.82
    ↵↵
    0.69
    した
    0.64
    ने
    0.64
    5
    0.63
    ة
    0.58
    0
    0.56
    ละ
    0.55
    </strong>
    0.53
    9
    0.53
    POSITIVE LOGITS
     spacers
    0.80
     Spacer
    0.72
     échantillons
    0.71
    م
    0.71
    m
    0.66
    eture
    0.65
     جميعا
    0.64
    𝐦
    0.64
    quels
    0.63
    т
    0.63
    Activations Density 0.000%

    No Known Activations