© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 140933
    Prev
    Next
    INDEX
    Explanations

    categorized for clarity

    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
    funktion
    0.36
    хбет
    0.36
     hashedPassword
    0.34
    。</
    0.33
     시간
    0.33
    ১৬
    0.33
     Yugoslavia
    0.33
     esquema
    0.33
    ಯ್ಯ
    0.33
     योग्यता
    0.32
    POSITIVE LOGITS
    H
    0.49
    e
    0.47
    K
    0.44
    F
    0.43
    L
    0.43
     for
    0.40
    S
    0.40
    D
    0.39
    J
    0.38
    W
    0.38
    Activations Density 0.143%

    No Known Activations