© 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. 32277
    Prev
    Next
    INDEX
    Explanations

    preaching and messages

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

    output text only

    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
    ラベル
    0.47
     Можно
    0.45
    फा
    0.40
    मुझे
    0.40
     FACT
    0.39
    বাড়
    0.39
     Likewise
    0.39
    ">
    0.38
     igualmente
    0.38
     ア
    0.38
    POSITIVE LOGITS
    (;
    0.43
    ("")
    0.43
     (!)
    0.42
     haired
    0.42
     उनको
    0.41
    (!)
    0.41
    asiti
    0.41
    (--
    0.40
    lesssim
    0.40
     ক্ষীণ
    0.39
    Activations Density 0.000%

    No Known Activations