© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9652
    Prev
    Next
    INDEX
    Explanations

    like and comparisons

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

    finding likeness

    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_40_width_16k_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
    明らかに
    0.39
     यामुळे
    0.38
     আপাত
    0.38
    俻
    0.34
     sudd
    0.33
    明明
    0.33
     এছাড়া
    0.33
    哎
    0.33
     याची
    0.33
     رہنے
    0.33
    POSITIVE LOGITS
     like
    2.91
    就像
    2.64
    如同
    2.61
     Like
    2.52
     LIKE
    2.48
    Like
    2.47
     مانند
    2.33
    เหมือน
    2.31
     مثل
    2.28
    처럼
    2.23
    Activations Density 0.769%

    No Known Activations