© 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-16K
    7. 4518
    Prev
    Next
    INDEX
    Explanations

    titles followed by explanations

    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_16k_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
    Ბ
    0.37
    𝗺
    0.35
    逈
    0.34
    Atom
    0.34
    ज्ञात
    0.33
    cą
    0.33
    alk
    0.33
    ether
    0.33
    ign
    0.32
    muştur
    0.32
    POSITIVE LOGITS
    :
    0.57
     кантип
    0.53
     :
    0.50
    ：
    0.50
     FAQ
    0.50
     –
    0.49
     bagaimana
    0.48
     How
    0.47
     -
    0.47
     how
    0.47
    Activations Density 0.166%

    No Known Activations