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

    Neuronpedia

    Jacobian LensNEW
    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. 76749
    Prev
    Next
    INDEX
    Explanations

    rules, components, types

    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
    ведите
    0.61
    скай
    0.46
    Software
    0.46
    MPs
    0.46
     inverse
    0.44
    𝘻
    0.44
    пси
    0.44
    ედ
    0.43
    пе
    0.42
    вих
    0.42
    POSITIVE LOGITS
    atk
    0.50
     upang
    0.45
    at
    0.45
     veya
    0.42
     নাকি
    0.42
    ı
    0.42
    .&
    0.42
    1
    0.41
    <unused80>
    0.40
     pomiędzy
    0.40
    Activations Density 0.003%

    No Known Activations