© 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. 231863
    Prev
    Next
    INDEX
    Explanations

    plant growth hormones

    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
    etet
    0.47
    老师
    0.46
    ელი
    0.43
    䚰
    0.41
    texts
    0.40
    ികൾ
    0.40
     Texte
    0.39
    كمل
    0.39
     جدول
    0.39
    拓展
    0.39
    POSITIVE LOGITS
    shr
    0.50
     slight
    0.44
    ロシア
    0.44
    ♬
    0.44
    Russia
    0.43
     boyut
    0.43
     strategically
    0.43
    撚
    0.43
    rylic
    0.43
     यूक्रेन
    0.42
    Activations Density 0.000%

    No Known Activations