© 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. 31-GEMMASCOPE-2-RES-262K
    4. 24888
    Prev
    Next
    INDEX
    Explanations

    numbering from the right

    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
    la
    0.46
     I
    0.44
    s
    0.44
    pn
    0.43
    borderColor
    0.42
     poolside
    0.42
     Continuing
    0.39
     Sharon
    0.39
    </b>
    0.38
     Scranton
    0.38
    POSITIVE LOGITS
    ೆಂಟ್
    0.51
     yil
    0.50
    ング
    0.48
     تاز
    0.47
    ныгы
    0.47
    브
    0.47
    ゴミ
    0.47
    영화
    0.46
     kalo
    0.45
    메
    0.45
    Activations Density 0.002%

    No Known Activations