© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54262
    Prev
    Next
    INDEX
    Explanations

    red boundary

    np_acts-logits-general · gemini-2.5-flash-lite

    bypassing strong points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.49
     recomb
    0.46
    卡的
    0.46
    melidir
    0.44
    んですよ
    0.43
    BBC
    0.43
    jvm
    0.43
    ATEG
    0.42
    位数
    0.42
     rehearse
    0.42
    POSITIVE LOGITS
     Macht
    0.47
     প্রান্ত
    0.44
    ე
    0.43
     Schall
    0.43
     Konzert
    0.41
    颀
    0.41
     ซึ่ง
    0.40
     নিষ
    0.40
     Tallinn
    0.40
     Wach
    0.40
    Activations Density 0.000%

    No Known Activations