© 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. 17277
    Prev
    Next
    INDEX
    Explanations

    animal

    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
    ký
    1.23
    𝙪
    1.21
    ။
    1.18
     nomes
    1.15
    在
    1.14
     informática
    1.09
    。
    1.09
    غ
    1.09
    ।
    1.07
    𝙮
    1.06
    POSITIVE LOGITS
    1.35
     I
    1.32
    ้
    1.20
    ized
    1.09
    した
    1.02
     Animals
    1.02
    कांड
    0.99
    ند
    0.97
    ે
    0.95
    ado
    0.92
    Activations Density 0.013%

    No Known Activations