© 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. 110708
    Prev
    Next
    INDEX
    Explanations

    local food, amplify both, code tiny

    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
     gia
    0.44
     Gia
    0.43
    »).
    0.41
     ib
    0.41
    മതി
    0.40
     deceduto
    0.40
     সাত
    0.40
    )},
    0.40
     تعدد
    0.40
    isee
    0.39
    POSITIVE LOGITS
    Ơ
    0.46
    B
    0.45
    Landscape
    0.44
    ב
    0.44
    𝚞
    0.43
    نوع
    0.43
    𝘢
    0.42
    A
    0.42
    G
    0.42
    M
    0.42
    Activations Density 0.011%

    No Known Activations